Get $1 credit for every $25 spent!

The Complete 2020 Big Data and Machine Learning Bundle

Ending In:
Add to Cart - $39.90
Add to Cart ($39.90)
$1,295
96% off
wishlist
Courses
10
Lessons
606
Enrolled
248

What's Included

Product Details

Access
Lifetime
Content
8.0 hours
Lessons
96

Elasticsearch & The Elastic Stack: In-Depth and Hands-On

Search, Analyze, & Visualize Big Data on a Cluster with Elasticsearch, Logstash, Beats, Kibana, and More

By Frank Kane | in Online Courses

Elasticsearch is a powerful tool not only for powering search on big websites but also for analyzing big data sets in a matter of milliseconds. It's an increasingly popular technology, and a valuable skill to have in today's job market. This comprehensive course covers it all, from installation to operations, with 60 lectures including 8 hours of video. Elasticsearch is positioning itself to be a much faster alternative to Hadoop, Spark, and Flink for many common data analysis requirements. It's an important tool to understand, and it's easy to use! Dive in and see what it's all about.

1,814 positive ratings from 11,737 students enrolled

  • Access 96 lectures & 8 hours of content 24/7
  • Set up search indices on an Elasticsearch cluster & querying that data in many ways
  • Import data into an Elasticsearch index
  • Stream data into Elasticsearch using Logstash & Filebeat
  • Bucket & analyze data & visualize it using the Elastic Stack's web UI, Kibana
  • Manage operations on your Elastic Stack using X-Pack to monitor your cluster's health

"The course is detailed and very well structured. It provides necessary insights and kick-starts your experience with the elastic stack." – Deepanshu Galyan

Frank Kane | Founder, Sundog Education

4.5/5 Instructor Rating: ★ ★ ★ ★

Frank Kane spent 9 years at Amazon and IMDb, developing and managing the technology that automatically delivers product and movie recommendations to hundreds of millions of customers, all the time. Frank holds 17 issued patents in the fields of distributed computing, data mining, and machine learning. In 2012, Frank left to start his own successful company, Sundog Software, which focuses on virtual reality environment technology and teaching others about big data analysis.

324,714 Total Students
77,009 Reviews

Important Details

  • Length of time users can access this course: lifetime
  • Access options: web & mobile streaming
  • Certification of completion included
  • Redemption deadline: redeem your code within 30 days of purchase
  • Updates included
  • Experience level required: intermediate

Requirements

  • Some familiarity with web services and REST
  • Some familiarity with Linux will be helpful
  • Exposure to JSON-formatted data will help

Course Outline

  • Your First Program

  • Installing and Understanding Elasticsearch

    • Section 1 Intro - 0:44
    • Installing Elasticsearch - 17:35
    • Elasticsearch Overview - 5:44
    • Intro to HTTP and RESTful API's - 11:48
    • Elasticsearch Basics: Logical Concepts - 1:58
    • Term Frequency / Inverse Document Frequency - 3:48
    • Using Elasticsearch - 3:59
    • What's New in Elasticsearch 7 - 3:41
    • How Elasticsearch Scales - 7:27
    • Quiz: Elasticsearch Concepts and Architecture - 4:08
    • Section 1 Wrapup - 0:30
  • Mapping and Indexing Data

    • Section 2 Intro - 0:36
    • Connecting to your Cluster - 7:03
    • Getting to Know the Movielens Data Set - 3:53
    • Analyzers - 8:27
    • Import a Single Movie via JSON / REST - 10:25
    • Insert Many Movies at Once - 5:29
    • Updating Data in Elasticsearch - 6:28
    • Deleting Data in Elasticsearch - 2:15
    • Insert, Update, and Delete a Fictitious Movie - 4:14
    • Dealing With Concurrency - 10:20
    • Using Analyzers and Tokenizers - 10:47
    • Data Modeling with Elasticsearch, Pt 1 - 5:24
    • Data Modeling with Elasticsearch, Pt 2 - 7:00
    • Section 2 Wrapup - 0:23
  • Searching with Elasticsearch

    • Section 3 Intro - 0:29
    • Using Query-String Search - 8:05
    • Using JSON Search - 10:13
    • Phrase Matching - 6:21
    • Querying in Different Ways - 4:25
    • Pagination - 6:18
    • Sorting - 7:54
    • More with Filters - 3:34
    • Using Filters - 2:39
    • Fuzzy Queries - 6:05
    • Partial Matching - 5:30
    • Query-time Search as you Type - 4:00
    • N-Grams, Part 1 - 5:16
    • N-Grams, Part 2 - 8:11
    • Section 3 Wrapup - 0:20
  • Importing Data Into Your Index - Big or Small

    • Section 4 Intro - 0:50
    • Importing Data from Scripts - 8:16
    • Importing with Client Libraries - 6:35
    • Importing with a Script Exercise - 3:55
    • Logstash Overview - 4:50
    • Installing Logstash - 8:57
    • Running Logstash - 5:11
    • Importing Data from MySQL using Logstash, Part 1 - 7:55
    • Importing Data from MySQL using Logstash, Part 2 - 7:47
    • Importing Data from AWS S3 using Logstash - 7:55
    • Integrating Kafka with Elasticsearch, Part 1 - 5:58
    • Integrating Kafka with Elasticsearch, Part 2 - 6:02
    • Elasticsearch and Apache Spark, Part 1 - 8:20
    • Elasticsearch and Apache Spark, Part 2 - 5:58
    • Import Movie Ratings from Spark to Elasticsearch - 8:48
    • Section 4 Wrapup - 0:36
  • Aggregation

    • Section 5 Intro - 0:59
    • Aggregations, Buckets and Metrics - 10:13
    • Histograms - 7:39
    • Aggregating Time Series Data - 6:03
    • Generating Histogram Data - 4:21
    • Nested Aggregations, Part 1 - 6:03
    • Nested Aggregations, Part 2 - 8:45
    • Section 5 Wrapup - 0:23
  • Using Kibana

    • Section 6 Intro - 0:20
    • Installing Kibana - 4:37
    • Analyzing Shakespeare with Kibana - 10:06
    • Exploring Data with Kibana - 3:19
    • Section 6 Wrapup - 0:21
  • Analyzing Log Data with the Elastic Stack

    • Section 7 Intro - 0:31
    • FileBeat and the Elastic Stack Architecture - 7:33
    • X-Pack Security - 3:10
    • Install, Configure, and Use FileBeat - 5:58
    • Analyzing Server Logs with Kibana - 9:52
    • Log Analysis with Kibana - 5:25
    • Section 7 Wrapup - 0:31
  • Elasticsearch Operations

    • Section 8 Intro - 0:39
    • How Many Shards Should I Use? - 5:09
    • Scaling with New Indices - 4:02
    • Index Alias Rotation - 3:52
    • Index Lifecycle Management - 2:09
    • Choosing Your Hardware - 3:17
    • Heap Sizing - 3:14
    • Monitoring - 6:25
    • Elasticsearch SQL - 5:30
    • Practicing Failover, Part 1 - 7:12
    • Practicing Failover, Part 2 - 8:46
    • Snapshots - 9:51
    • Rolling Restarts - 6:39
    • Section 8 Wrapup - 0:29
  • Elasticsearch in the Cloud

    • Section 9 Intro - 0:58
    • Using Amazon Elasticsearch Service, Part 1 - 7:20
    • Using Amazon Elasticsearch Service, Part 2 - 5:32
    • Using Elastic Cloud - 9:48
    • Section 9 Wrapup - 0:11
  • You Made It!

    • I Made It! Now What? - 3:54

View Full Curriculum


Access
Lifetime
Content
3.0 hours
Lessons
35

Keras Bootcamp for Deep Learning & AI in Python

Master Keras: An Important Deep Learning Framework for Deep Learning & Artificial Intelligence

By Minerva Singh | in Online Courses

This is a full 3-hour Python Keras Neural Network & Deep Learning Boot Camp that will help you learn basic machine learning, neural networks and deep learning using one of the most important Deep Learning frameworks—Keras. This course is your complete guide to the practical machine and deep learning using the Keras framework in Python. This means, this course covers the important aspects of Keras (Google's powerful Deep Learning framework) and if you take this course, you can do away with taking other courses or buying books on Python Keras based data science.

4.8/5 rating on Udemy!

  • Access 35 lectures & 3 hours of content 24/7
  • Get started w/ Jupyter notebooks for implementing data science techniques in Python
  • Understand the basics of Keras syntax
  • Create artificial neural networks & deep learning structures w/ Keras
Note: Software not included

Minerva Singh | Bestselling Udemy Instructor & Data Scientist

4.2/5 Instructor Rating: ★ ★ ★ ★

Minerva Singh is a PhD graduate from Cambridge University where she specialized in Tropical Ecology. She is also a Data Scientist on the side. As a part of her research, she has to carry out extensive data analysis, including spatial data analysis using tools like R, QGIS, and Python. Minerva also holds an MPhil degree in Geography and Environment from Oxford University.

60,288 Total Students
10,120 Reviews

Important Details

  • Length of time users can access this course: lifetime
  • Access options: web & mobile streaming
  • Certification of completion included
  • Redemption deadline: redeem your code within 30 days of purchase
  • Updates included
  • Experience level required: intermediate

Requirements

  • Prior exposure to Python-based data science will be beneficial
  • Prior exposure to basic statistical concepts & implementation will be useful
  • Prior exposure to common machine learning terms such as cross-validations

Course Outline

  • Introduction to the Course
    • What is Keras? - 3:29
    • Data and Code
    • Python Data Science Environment - 10:57
    • For Mac Users - 4:05
    • Install Keras on Windows 10 - 5:16
    • Install Keras with Mac - 4:19
    • Written Keras Installation Instructions
  • Introduction to Python Data Science Packages
    • Python Packages For Data Science - 3:16
    • Introduction to Numpy - 3:46
    • Create Numpy - 10:51
    • Numpy for Statistical Operations - 7:23
    • Introduction to Pandas - 12:06
    • Read in CSV - 7:13
    • Read in Excel - 5:31
    • Basic Data Cleaning - 4:30
  • Some Basic Concepts
    • What is Machine Learning? - 5:32
    • Theory Behind ANN (Artificial Neural Network) and DNN (Deep Neural Networks) - 9:17
  • Unsupervised Learning With Tensorflow and Keras
    • What is Unsupervised Learning? - 5:32
    • Autoencoders for Unsupervised Classification - 1:46
    • Autoencoders in Keras (Simple) - 5:43
    • Autoencoders in Keras (Sparsity Constraints) - 4:32
  • Neural Network With Keras
    • Multi Layer Perceptron (MLP) With Keras - 3:31
    • Keras MLP For Binary Classification - 4:01
    • Keras MLP for Multiclass Classification - 6:01
    • Keras MLP for Regression - 3:27
  • Deep Learning For Tensorflow & Keras
    • DNN Classifier With Keras - 3:30
    • DNN Classifier With Keras-Example 2 - 4:23
  • Convolutional Neural Networks (CNN)
    • What are CNNs? - 11:25
    • Implement a CNN With Keras - 4:04
    • CNN on Image Data with Keras-Part 2 - 5:05
  • Autoencoders with Convolution Neural Networks (CNN)
    • Autoencoders With CNN-Tensorflow - 7:15
    • Autoencoders With CNN- Keras - 4:46
  • Recurrent Neural Network (RNN)
    • Introduction to RNN - 5:40
    • LSTM for Time Series - 6:24
    • LSTM for Stock Prices - 7:21

View Full Curriculum


Access
Lifetime
Content
2.0 hours
Lessons
25

Machine Learning for Absolute Beginners - Level 1

Learn the Basics of Machine Learning & AI Even with No Prior Knowledge

By Idan Gabrieli | in Online Courses

The concept of AI and ML can be a little bit intimidating for beginners, and specifically for people without a substantial background in complex math and programming. This training is a soft starting point to walk you through the fundamental theoretical concepts. You'll be familiar with the basic definition of concepts then gradually move on to the most basic applications.

256 positive ratings from 20,567 students enrolled

  • Access 25 lectures & 2 hours of content 24/7
  • Understand what AI, Machine Learning & Deep Learning are
  • Differentiate Applied AI from Generalized AI
  • Learn about clustering & dimensions reduction

"The course is focusing more on the concept which is good rather than diving to solving big regression sums and computing slopes of lines of least squares." – Kalyan Mukherjee

Idan Gabrieli | Entrepreneur | Cloud Expert

4.2/5 Instructor Rating: ★ ★ ★ ★

Idan Gabrieli is an experience solution engineer manager (B.Sc. and MBA) with a comprehensive technical background in a variety of technologies. Idan is working with hundreds of business companies worldwide while helping to transform business challenges, requirements, and opportunities into practical use cases.

As part of his passion for sharing years of experience and knowledge, he created multiple online courses about a variety of topics while teaching thousands of students worldwide.

66,330 Total Students
2,158 Reviews

Important Details

  • Length of time users can access this course: lifetime
  • Access options: web & mobile streaming
  • Certification of completion included
  • Redemption deadline: redeem your code within 30 days of purchase
  • Updates included
  • Experience level required: intermediate

Requirements

  • Any device with basic specifications

Course Outline

  • Getting Started
    • Welcome! - 6:38
  • The Rise of Artificial Intelligence
    • AI is Coming... - 4:22
    • Artificial Intelligence - 6:14
    • Classical Programming - 3:12
    • Machine Learning - 7:13
    • Deep Learning - 7:51
    • Applied vs. Generalized AI - 4:19
    • Why Now? - 9:21
    • Quick Check-Point #1
  • Introduction to Machine Learning
    • Overview - ML Terminology - 1:20
    • “Black Box” Metaphor - 3:04
    • Features and Labels - 5:09
    • Training a Model - 4:49
    • Aiming for Generalization - 11:23
    • Quick Check-Point #2
  • Classification of ML Systems
    • The Degree of Supervision - 1:44
    • #1 - Supervised Learning - 6:16
    • Classification - 5:23
    • Regression - 7:13
    • Quick Check-Point #3
    • #2 - Unsupervised Learning - 3:40
    • Clustering - 5:09
    • Dimension Reduction - 5:48
    • Quick Check-Point #4
    • #3 - Reinforcement Learning - 5:57
    • Decision-Making Agent - 7:04
    • Quick Check-Point #5
  • Course Summary
    • Let's Recap and Thank You! - 6:40

View Full Curriculum


Access
Lifetime
Content
6.0 hours
Lessons
35

Taming Big Data with Spark Streaming& Scala: Hands-On

Process Massive Streams of Data in Real Time & Start Working Towards a Career in Big Data

By Frank Kane | in Online Courses

Big Data analysis is an essential component of any company organization that works with mass amounts of data, and it's a constantly adapting and innovating field. Spark Streaming is a new and quickly developing technology for processing mass data sets in real-time. Whether it's clickstream data from a major website, sensor data from an Internet of Things deployment, financial data, or any other large stream of data, Spark Streaming has the capability to transform and analyze that data as it is created. The professional applications of this technology are obvious, and this course will get you up to speed not just in Spark Streaming, but in Big Data generally, so you can confidently start looking for high-paying Big Data jobs.

2,584 positive ratings from 18,655 students enrolled

  • Access 35 lectures & 6 hours of content 24/7
  • Get a crash course in the Scala programming language
  • Learn how Apache Spark operates on a cluster
  • Set up discretized streams w/ Spark Streaming & transform them as data is received
  • Analyze streaming data over sliding windows of time
  • Maintain stateful information across streams of data
  • Connect Spark Streaming w/ highly scalable source of data, including Kafka, Flume, & Kinesis
  • Dump streams of data in real-time to NoSQL databases such as Cassandra

Frank Kane | Founder, Sundog Education

4.5/5 Instructor Rating: ★ ★ ★ ★

Frank Kane spent 9 years at Amazon and IMDb, developing and managing the technology that automatically delivers product and movie recommendations to hundreds of millions of customers, all the time. Frank holds 17 issued patents in the fields of distributed computing, data mining, and machine learning. In 2012, Frank left to start his own successful company, Sundog Software, which focuses on virtual reality environment technology and teaching others about big data analysis.

324,714 Total Students
77,009 Reviews

Important Details

  • Length of time users can access this course: lifetime
  • Access options: web & mobile streaming
  • Certification of completion included
  • Redemption deadline: redeem your code within 30 days of purchase
  • Updates included
  • Experience level required: intermediate

Requirements

  • Any device with basic specifications

Course Outline

  • Getting Started
    • Introduction, and Getting Set Up - 17:27
    • Stream Live Tweets with Spark Streaming! - 14:11
  • A Crash Course in Scala
    • Scala Basics: Part 1 - 11:26
    • Scala Basics: Part 2 - 9:41
    • Flow Control in Scala - 7:18
    • Functions in Scala - 8:47
    • Data Structures in Scala - 16:38
  • Spark Streaming Concepts
    • Introduction to Spark - 7:06
    • The Resilient Distributed Dataset (RDD) - 10:40
    • RDD's in Action: Simple Word Count Application - 8:17
    • Introduction to Spark Streaming - 6:32
    • Revisiting the PrintTweets Application - 5:10
    • Windowing: Aggregating Data over Longer Time Spans - 5:00
    • Fault Tolerance in Spark Streaming - 6:06
  • Spark Streaming Examples with Twitter
    • Saving Tweets to Disk - 13:24
    • Tracking the Average Tweet Length - 8:22
    • Tracking the Most Popular Hashtags - 14:50
  • Spark Streaming Examples with Clickstream / Apache Access Log Data
    • Tracking the Top URL's Requested - 13:27
    • Alarming on Log Errors - 11:56
    • Integrating Spark Streaming with SparkSQL - 15:03
    • Intro to Structured Streaming in Spark 2 - 8:27
    • [Activity] Analyzing Apache Log files with Structured Streaming - 11:24
  • Integrating with Other Systems
    • Integrating with Apache Kafka - 12:20
    • Integrating with Apache Flume - 8:51
    • Integrating with Amazon Kinesis - 5:29
    • Writing Custom Data Receivers - 6:55
    • Integrating with Cassandra - 7:35
  • Advanced Spark Streaming Examples
    • Stateful Information in Spark Streams - 15:07
    • Streaming K-Means Clustering - 15:36
    • Streaming Linear Regression - 11:50
  • Spark Streaming in Production
    • Running with spark-submit - 10:37
    • Packaging your Code with SBT - 17:17
    • Running on a Real Hadoop Cluster with EMR - 12:56
    • Troubleshooting and Tuning Spark Jobs - 12:35
  • You Made It!
    • Learning More - 3:44

View Full Curriculum


Access
Lifetime
Content
14.0 hours
Lessons
104

Data Science, Deep Learning, & Machine Learning with Python: Hands-On

Complete Hands-On Machine Learning Tutorial with Data Science, Tensorflow, AI, & Neural Networks

By Frank Kane | in Online Courses

Machine Learning and artificial intelligence (AI) is everywhere; if you want to know how companies like Google, Amazon, and even Udemy extract meaning and insights from massive data sets, this data science course will give you the fundamentals you need. If you've got some programming or scripting experience, this course will teach you the techniques used by real data scientists and machine learning practitioners in the tech industry - and prepare you for a move into this hot career path.

20,813 positive ratings from 126,185 students enrolled

  • Access 104 lectures & 14 hours of content 24/7
  • Build artificial neural networks w/ Tensorflow & Keras
  • Make predictions using linear regression, polynomial regression, & multivariate regression
  • Implement machine learning at massive scale w/ Apache Spark's MLLib
  • Design and evaluate A/B tests using T-Tests and P-Values

"Very comprehensive course on the basics of data science and ML. The instructor explains everything in a clear yet accurate way." – Gabriel Alfranca Ramón

Frank Kane | Founder, Sundog Education

4.5/5 Instructor Rating: ★ ★ ★ ★

Frank Kane spent 9 years at Amazon and IMDb, developing and managing the technology that automatically delivers product and movie recommendations to hundreds of millions of customers, all the time. Frank holds 17 issued patents in the fields of distributed computing, data mining, and machine learning. In 2012, Frank left to start his own successful company, Sundog Software, which focuses on virtual reality environment technology and teaching others about big data analysis.

324,714 Total Students
77,009 Reviews

Important Details

  • Length of time users can access this course: lifetime
  • Access options: web & mobile streaming
  • Certification of completion included
  • Redemption deadline: redeem your code within 30 days of purchase
  • Updates included
  • Experience level required: intermediate

Requirements

  • Any device with basic specifications

Course Outline

  • Getting Started
    • Introduction - 2:41
    • [Activity] WINDOWS: Installing and Using Anaconda & Course Materials - 10:43
    • [Activity] MAC: Installing and Using Anaconda & Course Materials - 8:17
    • [Activity] LINUX: Installing and Using Anaconda & Course Materials - 9:11
    • Python Basics, Part 1 - 4:59
    • Python Basics, Part 2 - 5:17
    • Python Basics, Part 3 - 2:46
    • Python Basics, Part 4 - 4:02
    • Introducing the Pandas Library - 10:08
  • Statistics and Probability Refresher, and Python Practice
    • Types Of Data - 6:58
    • Mean, Median, Mode - 5:26
    • Using mean, median, and mode in Python - 8:20
    • Variation and Standard Deviation - 11:12
    • Probability Density Function; Probability Mass Function - 3:27
    • Common Data Distributions - 7:45
    • Percentiles and Moments - 12:33
    • A Crash Course in matplotlib - 13:46
    • Advanced Visualization with Seaborn - 17:30
    • Covariance and Correlation - 11:31
    • Conditional Probability - 16:04
    • Exercise Solution: Conditional Probability of Purchase by Age - 2:20
    • Bayes' Theorem - 5:23
  • Predictive Models
    • Linear Regression - 11:01
    • Polynomial Regression - 8:04
    • Multiple Regression, and Predicting Car Prices - 11:26
    • Multi-Level Models - 4:36
  • Machine Learning with Python
    • Supervised vs. Unsupervised Learning, and Train/Test - 8:57
    • Using Train/Test to Prevent Overfitting a Polynomial Regression - 5:47
    • Bayesian Methods: Concepts - 3:59
    • Implementing a Spam Classifier with Naive Bayes - 8:05
    • K-Means Clustering - 7:23
    • Clustering people based on income and age - 5:14
    • Measuring Entropy - 3:09
    • WINDOWS: Installing GraphViz - 0:22
    • MAC: Installing GraphViz - 1:16
    • LINUX: Installing GraphViz - 0:54
    • Decision Trees: Concepts - 8:43
    • Decision Trees: Predicting Hiring Decisions - 9:47
    • Ensemble Learning - 5:59
    • XGBoost - 15:29
    • Support Vector Machines (SVM) Overview - 4:27
    • Using SVM to cluster people using scikit-learn - 8:38
  • Recommender System
    • User-Based Collaborative Filtering - 7:57
    • Item-Based Collaborative Filtering - 8:15
    • Finding Movie Similarities - 9:08
    • Improving the Results of Movie Similarities - 7:59
    • Making Movie Recommendations to People - 10:22
    • Improve the recommender's results - 5:29
  • More Data Mining and Machine Learning Techniques
    • K-Nearest-Neighbors: Concepts - 3:44
    • Using KNN to predict a rating for a movie - 12:29
    • Dimensionality Reduction; Principal Component Analysis - 5:44
    • PCA Example with the Iris data set - 9:05
    • Data Warehousing Overview: ETL and ELT - 9:05
    • Reinforcement Learning - 12:44
    • Reinforcement Learning & Q-Learning with Gym - 12:56
    • Understanding a Confusion Matrix - 5:17
    • Measuring Classifiers (Precision, Recall, etc.) - 6:40
  • Dealing with Real-World Data
    • Bias/Variance Tradeoff - 6:15
    • K-Fold Cross-Validation to avoid overfitting - 10:26
    • Data Cleaning and Normalization - 7:10
    • Cleaning web log data - 10:56
    • Normalizing numerical data - 3:22
    • Detecting outliers - 6:21
    • Feature Engineering and the Curse of Dimensionality - 6:03
    • Imputation Techniques for Missing Data - 7:48
    • Handling Unbalanced Data - 5:35
    • Binning, Transforming, Encoding, Scaling, and Shuffling - 7:51
  • Apache Spark: Machine Learning on Big Data
    • Installing Spark - Part 1 - 6:59
    • Installing Spark - Part 2 - 7:20
    • Spark Introduction - 9:10
    • Spark and the Resilient Distributed Dataset (RDD) - 11:42
    • Introducing MLLib - 5:09
    • Decision Trees in Spark - 16:15
    • K-Means Clustering in Spark - 11:23
    • TF / IDF - 6:43
    • Searching Wikipedia with Spark - 8:21
    • Using the Spark 2.0 DataFrame API for MLLib - 8:07
  • Experimental Design
    • Deploying Models to Real-Time Systems - 8:42
    • A/B Testing Concepts - 8:23
    • T-Tests and P-Values - 5:59
    • Hands-on With T-Tests - 6:04
    • Determining How Long to Run an Experiment - 3:24
    • A/B Test Gotchas - 9:26
  • Deep Learning and Neural Networks
    • Deep Learning Pre-Requisites - 11:43
    • The History of Artificial Neural Networks - 11:14
    • Deep Learning in the Tensorflow Playground - 12:00
    • Deep Learning Details - 9:29
    • Introducing Tensorflow - 11:29
    • Using Tensorflow, Part 1 - 13:10
    • Using Tensorflow, Part 2 - 12:03
    • Introducing Keras - 13:33
    • Using Keras to Predict Political Parties - 12:05
    • Convolutional Neural Networks (CNN's) - 11:27
    • Using CNN's for handwriting recognition - 8:02
    • Recurrent Neural Networks (RNN's) - 11:02
    • Using a RNN for sentiment analysis - 9:37
    • Transfer Learning - 12:14
    • Tuning Neural Networks - 4:39
    • Deep Learning Regularization Techniques - 6:21
    • The Ethics of Deep Learning - 11:02
    • Learning More about Deep Learning - 1:44
  • Final Project
    • Your final project assignment - 6:19
    • Final project review - 10:26
  • You made it!
    • More to Explore - 2:59

View Full Curriculum


Access
Lifetime
Content
7.0 hours
Lessons
52

Apache Spark 3.0 with Scala: Hands-On with Big Data

Dive Right In with 20+ Hands-On Examples of Analyzing Large Data Sets with Apache Spark

By Frank Kane | in Online Courses

“Big data" analysis is a hot and highly valuable skill – and this course will teach you the hottest technology in big data: Apache Spark. Employers including Amazon, eBay, NASA JPL, and Yahoo all use Spark to quickly extract meaning from massive data sets across a fault-tolerant Hadoop cluster. You'll learn those same techniques, using your own Windows system right at home. It's easier than you might think, and you'll be learning from an ex-engineer and senior manager from Amazon and IMDb.

10,873 positive ratings from 55,513 students enrolled

  • Access 52 lectures & 7 hours of content 24/7
  • Frame big data analysis problems as Apache Spark scripts
  • Optimize Spark jobs through partitioning, caching, & other techniques
  • Process continula streams of data w/ Spark Streaming
  • Develop distributed code using the Scala programming language

Frank Kane | Founder, Sundog Education

4.5/5 Instructor Rating: ★ ★ ★ ★

Frank Kane spent 9 years at Amazon and IMDb, developing and managing the technology that automatically delivers product and movie recommendations to hundreds of millions of customers, all the time. Frank holds 17 issued patents in the fields of distributed computing, data mining, and machine learning. In 2012, Frank left to start his own successful company, Sundog Software, which focuses on virtual reality environment technology and teaching others about big data analysis.

324,714 Total Students
77,009 Reviews

Important Details

  • Length of time users can access this course: lifetime
  • Access options: web & mobile streaming
  • Certification of completion included
  • Redemption deadline: redeem your code within 30 days of purchase
  • Updates included
  • Experience level required: intermediate

Requirements

  • Any device with basic specifications

Course Outline

  • Getting Started
    • Introduction, and Getting Set Up - 16:19
    • Create a Histogram of Real Movie Ratings with Spark! - 14:39
  • Scala Crash Course
    • Scala Basics, Part 1
    • Scala Basics, Part 2 - 9:41
    • Flow Control in Scala - 7:18
    • Functions in Scala - 8:47
    • Data Structures in Scala - 16:38
  • Spark Basics and Simple Examples
    • Introduction to Spark - 8:42
    • The Resilient Distributed Dataset - 11:06
    • Ratings Histogram Walkthrough - 7:35
    • Spark Internals - 4:44
    • Key / Value RDD's, and the Average Friends by Age example - 12:23
    • Running the Average Friends by Age Example - 8:00
    • Filtering RDD's, and the Minimum Temperature by Location Example - 6:45
    • Running the Minimum Temperature Example, and Modifying it for Maximum - 10:12
    • Counting Word Occurrences using Flatmap() - 9:01
    • Improving the Word Count Script with Regular Expressions - 6:43
    • Sorting the Word Count Results - 8:12
    • Find the Total Amount Spent by Customer - 3:38
    • Check your Results, and Sort Them by Total Amount Spent - 4:28
    • Check Your Results and Implementation Against Mine - 3:26
  • Advanced Examples of Spark Programs
    • Find the Most Popular Movie - 4:31
    • Use Broadcast Variables to Display Movie Names - 8:54
    • Find the Most Popular Superhero in a Social Graph - 14:12
    • Superhero Degrees of Separation: Introducing Breadth-First Search - 6:54
    • Superhero Degrees of Separation: Accumulators, and Implementing BFS in Spark - 5:55
    • Superhero Degrees of Separation: Review the code, and run it! - 10:43
    • Item-Based Collaborative Filtering in Spark, cache(), and persist() - 8:18
    • Running the Similar Movies Script using Spark's Cluster Manager - 14:15
    • Improve the Quality of Similar Movies - 2:42
  • Running Spark on a Cluster
    • Using spark-submit to run Spark driver scripts - 7:00
    • Packaging driver scripts with SBT - 13:14
    • Introducing Amazon Elastic MapReduce - 7:13
    • Creating Similar Movies from One Million Ratings on EMR - 11:33
    • Partitioning - 5:09
    • Best Practices for Running on a Cluster - 5:33
    • Troubleshooting, and Managing Dependencies - 9:10
  • SparkSQL, DataFrames, and DataSets
    • Introduction to SparkSQL - 7:10
    • Using SparkSQL - 7:03
    • Using DataFrames and DataSets - 6:38
    • Using DataSets instead of RDD's - 7:24
  • Machine Learning with MLLib
    • Introducing MLLib - 9:18
    • If you have trouble running the following activity...
    • Using MLLib to Produce Movie Recommendations - 14:35
    • Linear Regression with MLLib - 5:55
    • Using DataFrames with MLLib - 8:30
  • Intro to Spark Streaming
    • Spark Streaming Overview - 9:55
    • Set up a Twitter Developer Account, and Stream Tweets - 12:44
    • Structured Streaming - 4:17
  • Intro to GraphX
    • GraphX, Pregel, and Breadth-First-Search with Pregel. - 10:40
    • Superhero Degrees of Separation using GraphX - 9:01
  • You Made It! Where to Go from Here.
    • Learning More, and Career Tips - 4:15

View Full Curriculum


Access
Lifetime
Content
14.0 hours
Lessons
98

The Ultimate Hands-On Hadoop: Tame your Big Data

Hadoop Tutorial with MapReduce, HDFS, Spark, Flink, Hive, HBase, MongoDB, Cassandra, Kafka + More!

By Frank Kane | in Online Courses

The world of Hadoop and "Big Data" can be intimidating - hundreds of different technologies with cryptic names form the Hadoop ecosystem. With this Hadoop tutorial, you'll not only understand what those systems are and how they fit together - but you'll go hands-on and learn how to use them to solve real business problems! Learn and master the most popular big data technologies in this comprehensive course, taught by a former engineer and senior manager from Amazon and IMDb. We'll go way beyond Hadoop itself, and dive into all sorts of distributed systems you may need to integrate with.

19,912 positive ratings from 107,065 students enrolled

  • Access 98 lectures & 14 hours of content 24/7
  • Design distributed systems that manage "big data" using Hadoop a& related technologies
  • Use Pig & Spark to create scripts to process data on a Hadoop cluster in more complex ways
  • Analyze non-relational data using HBase, Cassandra, & MongoDB
  • Use HDFS & MapReduce for storing and analyzing data at scale

"Excellent introduction to the big data technologies delivered in a very professional manner. Frank is an amazing instructor. I would highly recommend this course to anyone who wants to dive in the world of big data." – Sangam Batra

Frank Kane | Founder, Sundog Education

4.5/5 Instructor Rating: ★ ★ ★ ★

Frank Kane spent 9 years at Amazon and IMDb, developing and managing the technology that automatically delivers product and movie recommendations to hundreds of millions of customers, all the time. Frank holds 17 issued patents in the fields of distributed computing, data mining, and machine learning. In 2012, Frank left to start his own successful company, Sundog Software, which focuses on virtual reality environment technology and teaching others about big data analysis.

324,714 Total Students
77,009 Reviews

Important Details

  • Length of time users can access this course: lifetime
  • Access options: web & mobile streaming
  • Certification of completion included
  • Redemption deadline: redeem your code within 30 days of purchase
  • Updates included
  • Experience level required: intermediate

Requirements

  • Any device with basic specifications

Course Outline

  • Learn all the buzzwords! And install Hadoop.
    • Tips for Using This Course - 1:09
    • If you have trouble downloading Hortonworks...
    • Introduction, and install Hadoop on your desktop - 19:03
    • The Hortonworks and Cloudera Merger, and how it affects this course. - 3:01
    • Hadoop Overview and History - 7:44
    • Overview of the Hadoop Ecosystem - 16:48
  • Using Hadoop's Core: HDFS and MapReduce
    • HDFS: What it is, and how it works - 13:56
    • Install the MovieLens dataset into HDFS using the Ambari UI - 6:22
    • Install the MovieLens dataset into HDFS using the command line - 7:52
    • MapReduce: What it is, and how it works - 10:42
    • How MapReduce distributes processing - 12:59
    • MapReduce example: Break down movie ratings by rating score - 11:37
    • Troubleshooting tips: installing pip and mrjob
    • Installing Python, MRJob, and nano - 7:43
    • Code up the ratings histogram MapReduce job and run it - 7:36
    • Rank movies by their popularity - 7:06
    • Check your results against mine! - 8:25
  • Programming Hadoop with Pig
    • Introducing Ambari - 9:49
    • Introducing Pig - 6:27
    • Example: Find the oldest movie with a 5-star rating using Pig - 15:09
    • Find old 5-star movies with Pig - 9:42
    • More Pig Latin - 7:36
    • Find the most-rated one-star movie - 1:56
    • Pig Challenge: Compare Your Results to Mine! - 5:39
  • Programming Hadoop with Spark
    • Why Spark? - 10:08
    • The Resilient Distributed Dataset (RDD) - 10:14
    • Find the movie with the lowest average rating - with RDD's - 15:33
    • Datasets and Spark 2.0 - 6:30
    • Find the movie with the lowest average rating - with DataFrames - 10:02
    • Movie recommendations with MLLib - 12:18
    • Filter the lowest-rated movies by number of ratings - 2:52
    • Check your results against mine! - 6:42
  • Using Relational Data Stores with Hadoop
    • What is Hive? - 6:33
    • Use Hive to find the most popular movie - 10:45
    • How Hive works - 9:12
    • Use Hive to find the movie with the highest average rating - 1:56
    • Compare your solution to mine. - 4:12
    • Integrating MySQL with Hadoop - 8:02
    • Install MySQL and import our movie data - 7:45
    • Use Sqoop to import data from MySQL to HFDS/Hive - 7:33
    • Use Sqoop to export data from Hadoop to MySQL - 7:18
  • Using non-relational data stores with Hadoop
    • Why NoSQL? - 13:57
    • What is HBase - 12:57
    • Import movie ratings into HBase - 13:30
    • Use HBase with Pig to import data at scale. - 11:21
    • Cassandra overview - 14:53
    • If you have trouble installing Cassandra...
    • Installing Cassandra - 11:46
    • Write Spark output into Cassandra - 11:02
    • MongoDB overview - 16:56
    • Install MongoDB, and integrate Spark with MongoDB - 12:46
    • Using the MongoDB shell - 7:50
    • Choosing a database technology - 16:01
    • Choose a database for a given problem - 5:02
  • Querying your Data Interactively
    • Overview of Drill - 7:57
    • Setting up Drill - 10:58
    • Querying across multiple databases with Drill - 7:09
    • Overview of Phoenix - 8:57
    • Install Phoenix and query HBase with it - 7:10
    • Integrate Phoenix with Pig - 11:47
    • Overview of Presto - 6:41
    • Install Presto, and query Hive with it. - 12:29
    • Query both Cassandra and Hive using Presto. - 9:03
  • Managing your Cluster
    • YARN explained - 10:03
    • Tez explained - 4:58
    • Use Hive on Tez and measure the performance benefit - 8:37
    • Mesos explained - 7:15
    • ZooKeeper explained - 13:12
    • Simulating a failing master with ZooKeeper - 6:49
    • Oozie explained - 11:58
    • Set up a simple Oozie workflow - 16:41
    • Zeppelin overview - 5:04
    • Use Zeppelin to analyze movie ratings, part 1 - 12:28
    • Use Zeppelin to analyze movie ratings, part 2 - 9:48
    • Hue overview - 8:08
    • Other technologies worth mentioning - 4:37
  • Feeding Data to your Cluster
    • Kafka explained - 9:50
    • Setting up Kafka, and publishing some data. - 7:24
    • Publishing web logs with Kafka - 10:23
    • Flume explained - 10:18
    • Set up Flume and publish logs with it. - 7:46
    • Set up Flume to monitor a directory and store its data in HDFS - 9:14
  • Analyzing Streams of Data
    • Spark Streaming: Introduction - 14:29
    • Analyze web logs published with Flume using Spark Streaming - 14:22
    • Monitor Flume-published logs for errors in real time - 2:02
    • Exercise solution: Aggregating HTTP access codes with Spark Streaming - 4:26
    • Apache Storm: Introduction - 9:29
    • Count words with Storm - 14:37
    • Flink: An Overview - 6:55
    • Counting words with Flink - 10:22
  • Designing Real-World Systems
    • Best Of The Rest - 9:26
    • Review: How the pieces fit together - 6:31
    • Understanding your requirements - 8:04
    • Sample application: consume webserver logs and keep track of top-sellers - 10:08
    • Sample application: serving movie recommendations to a website - 11:20
    • Design a system to report web sessions per day - 2:53
    • Exercise solution: Design a system to count daily sessions - 4:26
  • Learning More
    • Books and online resources - 5:32

View Full Curriculum


Access
Lifetime
Content
4.0 hours
Lessons
51

Taming Big Data with MapReduce & Hadoop

Analyze Large Amounts of Data with Today's Top Big Data Technologies

By Frank Kane | in Online Courses

Big data is hot, and data management and analytics skills are your ticket to a fast-growing, lucrative career. This course will quickly teach you two technologies fundamental to big data: MapReduce and Hadoop. Learn and master the art of framing data analysis problems as MapReduce problems with over 10 hands-on examples. Write, analyze, and run real code along with the instructor– both on your own system, and in the cloud using Amazon's Elastic MapReduce service. By course's end, you'll have a solid grasp of data management concepts.

2,337 positive ratings from 19,533 students enrolled

  • Access 51 lectures & 4 hours of content 24/7
  • Run MapReduce jobs quickly using Python & MRJob
  • Translate complex analysis problems into multi-stage MapReduce jobs
  • Scale up to larger data sets using Amazon's Elastic MapReduce service
  • Understand how Hadoop distributes MapReduce across computing clusters
  • Complete projects to get hands-on experience: analyze social media data, movie ratings & more
  • Learn about other Hadoop technologies, like Hive, Pig & Spark

"This course is excellent! It is the clearest explanation for the map reduce concept that I have ever heard." – Philip Solvyev

Frank Kane | Founder, Sundog Education

4.5/5 Instructor Rating: ★ ★ ★ ★

Frank Kane spent 9 years at Amazon and IMDb, developing and managing the technology that automatically delivers product and movie recommendations to hundreds of millions of customers, all the time. Frank holds 17 issued patents in the fields of distributed computing, data mining, and machine learning. In 2012, Frank left to start his own successful company, Sundog Software, which focuses on virtual reality environment technology and teaching others about big data analysis.

324,714 Total Students
77,009 Reviews

Important Details

  • Length of time users can access this course: lifetime
  • Access options: web & mobile streaming
  • Certification of completion included
  • Redemption deadline: redeem your code within 30 days of purchase
  • Updates included
  • Experience level required: intermediate

Requirements

  • Any device with basic specifications

Course Outline

  • Introduction
    • Introduction - 3:22
  • Getting Started
    • New Setup Instructions!
    • Installing Enthought Canopy - 7:44
  • Understanding MapReduce
    • MapReduce Basic Concepts - 13:25
    • Walkthrough of Rating Histogram Code - 10:38
    • Understanding How MapReduce Scales / Distributed Computing - 3:00
    • Average Friends by Age Example: Part 1 - 3:04
    • Average Friends by Age Example: Part 2 - 7:13
    • Minimum Temperature By Location Example - 9:39
    • Maximum Temperature By Location Example - 3:22
    • Word Frequency in a Book Example - 5:25
    • Making the Word Frequency Mapper Better with Regular Expressions - 3:15
    • Sorting the Word Frequency Results Using Multi-Stage MapReduce Jobs - 8:18
    • Activity: Design a Mapper and Reducer for Total Spent by Customer - 2:54
    • Activity: Write Code for Total Spent by Customer - 3:57
    • Compare Your Code to Mine. Activity: Sort Results by Amount Spent - 5:38
    • Compare your Code to Mine for Sorted Results. - 3:49
    • Combiners - 7:26
  • Advanced MapReduce Examples
    • Example: Most Popular Movie - 7:23
    • Including Ancillary Lookup Data in the Example - 8:00
    • Example: Most Popular Superhero, Part 1 - 4:22
    • Example: Most Popular Superhero, Part 2 - 6:31
    • Example: Degrees of Separation: Concepts - 12:27
    • Degrees of Separation: Preprocessing the Data - 5:14
    • Degrees of Separation: Code Walkthrough - 6:34
    • Degrees of Separation: Running and Analyzing the Results - 5:41
    • Example: Similar Movies Based on Ratings: Concepts - 7:24
    • Similar Movies: Code Walkthrough - 7:16
    • Similar Movies: Running and Analyzing the Results - 6:37
    • Learning Activity: Improving our Movie Similarities MapReduce Job - 3:58
  • Using Hadoop and Elastic MapReduce
    • Fundamental Concepts of Hadoop - 5:59
    • The Hadoop Distributed File System (HDFS) - 3:09
    • Apache YARN - 4:20
    • Hadoop Streaming: How Hadoop Runs your Python Code - 3:37
    • Setting Up Your Amazon Elastic MapReduce Account - 6:49
    • Linking Your EMR Account with MRJob - 3:40
    • Exercise: Run Movie Recommendations on Elastic MapReduce - 4:34
    • Analyze the Results of Your EMR Job
  • Advanced Hadoop and EMR
    • Distributed Computing Fundamentals - 4:33
    • Activity: Running Movie Similarities on Four Machines - 4:27
    • Analyzing the Results of the 4-Machine Job - 5:44
    • Troubleshooting Hadoop Jobs with EMR and MRJob, Part 1 - 4:01
    • Troubleshooting Hadoop Jobs, Part 2 - 10:28
    • Analyzing One Million Movie Ratings Across 16 Machines, Part 1 - 6:08
    • Analyzing One Million Movie Ratings Across 16 Machines, Part 2 - 8:02
  • Other Hadoop Technologies
    • Introducing Apache Hive - 6:16
    • Introducing Apache Pig - 3:26
    • Apache Spark: Concepts - 9:37
    • Spark Example: Part 1 - 11:15
    • Spark Example: Part 2 - 3:22
    • Congratulations! - 0:41

View Full Curriculum


Access
Lifetime
Content
5.0 hours
Lessons
48

Taming Big Data with Apache Spark & Python: Hands-On

Learn the Techniques Used by Major Companies to Manage Mass Data Sets

By Frank Kane | in Online Courses

Have you ever wondered how major companies and organizations manage all of the massive amounts of data they collect? The answer is Big Data technology, and Big Data engineers are in big-time demand. Major employers like Amazon, eBay, and NASA JPL use Apache Spark to extract data sets across a fault-tolerant Hadoop cluster. Sound complicated? That's why you should take this course, to learn these techniques and more, using your own system at home.

8,281 positive raitngs from 46,796 students enrolled

  • Access 48 lectures & 5 hours of content 24/7
  • Learn the concepts of Spark's Resilient Distributed Datastores
  • Develop & run Spark jobs quickly using Python
  • Translate complex analysis problems into iterative or multi-stage Spark scripts
  • Scale up to larger data sets using Amazon's Elastic MapReduce
  • Understand how Hadoop YARN distributes Spark across computing clusters
  • Learn about other Spark technologies, like Spark SQL, Spark Streaming, & GraphX

Frank Kane | Founder, Sundog Education

4.5/5 Instructor Rating: ★ ★ ★ ★

Frank Kane spent 9 years at Amazon and IMDb, developing and managing the technology that automatically delivers product and movie recommendations to hundreds of millions of customers, all the time. Frank holds 17 issued patents in the fields of distributed computing, data mining, and machine learning. In 2012, Frank left to start his own successful company, Sundog Software, which focuses on virtual reality environment technology and teaching others about big data analysis.

324,714 Total Students
77,009 Reviews

Important Details

  • Length of time users can access this course: lifetime
  • Access options: web & mobile streaming
  • Certification of completion included
  • Redemption deadline: redeem your code within 30 days of purchase
  • Updates included
  • Experience level required: intermediate

Requirements

  • Some prior programming or scripting experience

Course Outline

  • Getting Started with Spark
    • Introduction - 1:46
    • How to Use This Course - 1:41
    • [Activity] Getting Set Up: Installing Python, a JDK, Spark, and its Dependencies. - 14:41
    • [Activity] Installing the MovieLens Movie Rating Dataset - 3:35
    • [Activity] Run your first Spark program! Ratings histogram example. - 6:11
  • Spark Basics and Simple Examples
    • Introduction to Spark - 10:11
    • The Resilient Distributed Dataset (RDD) - 12:35
    • Ratings Histogram Walkthrough - 13:27
    • Key/Value RDD's, and the Average Friends by Age Example - 16:08
    • [Activity] Running the Average Friends by Age Example - 5:40
    • Filtering RDD's, and the Minimum Temperature by Location Example - 8:11
    • [Activity]Running the Minimum Temperature Example, and Modifying it for Maximums - 5:06
    • [Activity] Running the Maximum Temperature by Location Example - 3:19
    • [Activity] Counting Word Occurrences using flatmap() - 7:24
    • [Activity] Improving the Word Count Script with Regular Expressions - 4:42
    • [Activity] Sorting the Word Count Results - 7:46
    • [Exercise] Find the Total Amount Spent by Customer - 4:01
    • [Excercise] Check your Results, and Now Sort them by Total Amount Spent. - 5:09
    • Check Your Sorted Implementation and Results Against Mine. - 2:44
  • Advanced Examples of Spark Programs
    • [Activity] Find the Most Popular Movie - 5:53
    • [Activity] Use Broadcast Variables to Display Movie Names Instead of ID Numbers - 8:25
    • Find the Most Popular Superhero in a Social Graph - 4:29
    • [Activity] Run the Script - Discover Who the Most Popular Superhero is! - 6:00
    • Superhero Degrees of Separation: Introducing Breadth-First Search - 7:56
    • Superhero Degrees of Separation: Accumulators, and Implementing BFS in Spark - 6:44
    • [Activity] Superhero Degrees of Separation: Review the Code and Run it - 9:35
    • Item-Based Collaborative Filtering in Spark, cache(), and persist() - 10:10
    • [Activity] Running the Similar Movies Script using Spark's Cluster Manager - 10:55
    • [Exercise] Improve the Quality of Similar Movies - 3:05
  • Running Spark on a Cluster
    • Introducing Elastic MapReduce - 5:09
    • [Activity] Setting up your AWS / Elastic MapReduce Account and Setting Up PuTTY - 9:58
    • Partitioning - 4:21
    • Create Similar Movies from One Million Ratings - Part 1 - 5:10
    • [Activity] Create Similar Movies from One Million Ratings - Part 2 - 11:26
    • Create Similar Movies from One Million Ratings - Part 3 - 3:30
    • Troubleshooting Spark on a Cluster - 3:43
    • More Troubleshooting, and Managing Dependencies - 6:02
  • SparkSQL, DataFrames, and DataSets
    • Introducing SparkSQL - 6:08
    • Executing SQL commands and SQL-style functions on a DataFrame - 8:16
    • Using DataFrames instead of RDD's - 5:52
  • Other Spark Technologies and Libraries
    • Introducing MLLib - 8:09
    • [Activity] Using MLLib to Produce Movie Recommendations - 2:55
    • Analyzing the ALS Recommendations Results - 4:53
    • Using DataFrames with MLLib - 7:31
    • Spark Streaming - 8:04
    • [Activity] Structured Streaming in Python - 8:47
    • GraphX - 2:11
  • You Made It! Where to Go from Here.
    • Learning More about Spark and Data Science - 3:43

View Full Curriculum


Access
Lifetime
Content
5.0 hours
Lessons
62

Tensorflow Masterclass for Machine Learning & AI in Python

Master the Most Important Deep Learning Frameworks for Python Data Science

By Minerva Singh | in Online Courses

This course is your complete guide to the practical machine and deep learning using the Tensorflow and Keras frameworks in Python. In the age of Big Data, companies across the globe use Python to sift through the avalanche of information at their disposal and the advent of Tensorflow and Keras is revolutionizing deep learning. This course will help you break into this booming field.

344 positive ratings from 9,994 students enrolled

  • Access 62 lectures & 5 hours of content 24/7
  • Get a full introduction to Python Data Science
  • Get started w/ Jupyter notebooks for implementing data science techniques in Python Learn about Tensorflow & Keras installation
  • Understand the workings of Pandas & Numpy
  • Cover the basics of the Tensorflow syntax & graphing environment and Keras syntax
  • Discover how to create artificial neural networks & deep learning structures w/ Tensorflow & Keras
Note: Software not included

Minerva Singh | Bestselling Udemy Instructor & Data Scientist

4.2/5 Instructor Rating: ★ ★ ★ ★

Minerva Singh is a PhD graduate from Cambridge University where she specialized in Tropical Ecology. She is also a Data Scientist on the side. As a part of her research, she has to carry out extensive data analysis, including spatial data analysis using tools like R, QGIS, and Python. Minerva also holds an MPhil degree in Geography and Environment from Oxford University.

60,288 Total Students
10,120 Reviews

Important Details

  • Length of time users can access this course: lifetime
  • Access options: web & mobile streaming
  • Certification of completion included
  • Redemption deadline: redeem your code within 30 days of purchase
  • Updates included
  • Experience level required: intermediate

Requirements

  • Any device with basic specifications

Course Outline

  • Introduction to the Course
    • Welcome to the World of TensorFlow - 4:03
    • Data and Code
    • Anaconda:Python Data Science Environment
    • Anaconda Installation For Mac Users
    • Install Tensorflow - 15:12
    • Written Instructions for Tensorflow Install
  • Introduction to Python Data Science Packages
    • Commonly Used Python Data Science Packages - 3:16
    • What is Numpy? - 3:46
    • Create Numpy - 10:51
    • Numpy for Statistical Operations - 7:23
    • Introduction to Pandas - 12:06
    • Read in CSV - 7:13
    • Read in Excel - 5:31
    • Basic Data Preprocessing - 4:30
  • Introduction to Tensorflow
    • Start With Tensorflow - 2:36
    • Start With Tensorflow Computational Graphs - 2:56
    • Common Mathematical Operations
    • A Brief Tensorflow Session - 4:37
    • Interactive Tensorflow Session - 1:38
    • Constants and Variables in Tensorflow - 3:42
    • Placeholders in Tensorflow
    • TensorBoard: Visualize Graphs in TensorFlow - 2:44
    • Access TensorBoard Graphs - 2:55
  • Some Preliminary Tensorflow and Keras Applications
    • Ordinary Least Squares Linear Regression (OLS): Theory - 10:44
    • OLS From First Principles - 9:22
    • Visualize the Results of OLS - 3:28
    • OLS With Multiple Predictors With Tensorflow-Part 1 - 5:08
    • Estimate With Tensorflow Estimators - 3:05
    • Multiple Regression With Tensorflow Estimators - 5:24
    • More on Linear Regressor Estimator - 8:24
    • GLM: Generalized Linear Model - 5:25
    • Linear Classifier For Binary Classification - 9:33
    • Accuracy Assessment For Binary Classification - 4:19
    • Linear Classification with Binary Classification With Mixed Predictors - 8:15
  • Some Basic Concepts
    • Machine Learning: Theory
    • What Are ANN (Artificial Neural Network) and DNN (Deep Neural Networks)? - 9:17
  • Unsupervised and Supervised Learning With Tensorflow
    • What is Unsupervised Learning? - 5:32
    • K-means Clustering: Theory - 5:44
    • Implement K-Means on Real Data - 5:37
    • Softmax Classification - 7:35
    • Random Forests (RF) Theory - 7:14
    • Random Forest (RF) for Binary Classification - 7:09
    • Random Forest (RF) for Multiclass Classification - 5:07
    • kNN Theory
    • Implement kNN - 3:22
  • Neural Network for Tensorflow & Keras
    • Multi Layer Perceptron (MLP) with Tensorflow - 6:24
    • Multi Layer Perceptron (MLP) With Keras - 3:31
    • Keras MLP For Binary Classification - 4:01
    • Keras MLP for Multiclass Classification - 6:01
    • Keras MLP for Regression - 3:27
  • Deep Learning For Tensorflow & Keras
    • Deep Neural Network (DNN) Classifier With Tensorflow - 6:47
    • Deep Neural Network (DNN) Classifier With Mixed Predictors - 8:11
    • Deep Neural Network (DNN) Regression With Tensorflow - 5:24
    • New Lecture
    • Wide & Deep Learning (Tensorflow) - 11:34
    • DNN Classifier With Keras - 3:30
    • DNN Classifier With Keras-Example 2 - 4:23
  • Autoencoders with Convolution Neural Networks (CNN)
    • Autoencoders With CNN-Tensorflow - 7:15
    • Autoencoders With CNN- Keras - 4:46
  • Recurrent Neural Network (RNN)
    • Introduction to RNN - 5:40
    • LSTM for Time Series
    • LSTM for Stock Prices - 7:21

View Full Curriculum



Terms

  • Unredeemed licenses can be returned for store credit within 30 days of purchase. Once your license is redeemed, all sales are final.