Expanded

Advanced Machine Learning with ENCOG - Part 2

By Abhishek Kumar
In this course, you will learn to implement dimensionality reduction and clustering using self-organizing maps, pattern recall and reconstruction using Hopfield networks, time series forecasting using temporal dataset, and optimization using genetic algorithm. This course will not only provide you fundamental knowledge of aforementioned topics, but also will help you to implement these applications using ENCOG machine learning framework.
Get started
Course info
Rating
(56)
Level
Advanced
Updated
Mar 24, 2014
Duration
3h 41m
Table of contents
Course Introduction
Introduction 2m Course Scope 3m Course Structure 1m
Unsupervised Competitive Networks
Introduction 1m Outline 1m Unsupervised Learning 3m Unsupervised Learning Tasks 6m Unsupervised Networks 2m Self-Organizing Map (SOM) Introduction 2m Example Dataset 1m SOM Network Topology 4m SOM Training 8m SOM Training Using ENCOG 6m SOM Demo: Setup SOM Network (XAML Part) 5m SOM Demo: Setup SOM Network (Code Behind) 10m SOM Demo: Training SOM Network 4m SOM Demo: Overlay 5m SOM Demo: Alternative Visualization Approach 8m Applications of SOM 2m Other Unsupervised Learning Techniques 1m Summary 1m
Unsupervised Auto-Associative Networks
Introduction 1m Outline 1m Associative Memory 4m Types of Associative Memory 2m Hopfield Network Introduction 2m Hopfield Network Working 4m Hopfield Network in ENCOG 3m Demo: Memory Recall and Reconstruction 9m Applications of Hopfield Network 1m Summary 2m
Case Study: Time Series Forecasting
Introduction 1m Outline 1m Time Series Forecasting 3m Time Series Components 3m Forecasting Window 3m Forecasting Using Neural Networks 4m Forecasting Using ENCOG Framework: TemporalMLDataSet 1m Forecasting Using ENCOG Framework: TemporalDataDescription 3m Forecasting Using ENCOG Framework: TemporalPoint 2m Case Study: Time Series Forecasting 2m Demo: Time Series Forecasting - Introduction 5m Demo: Step 1 - Read Data 2m Demo: Step 2 - Normalize Data 1m Demo: Step 3 - Generate Temporal Data 2m Demo: Step 4 - Create and Train Neural Network 2m Demo: Step 5 - Evaluate Neural Network 8m Summary 2m
Optimization Using Genetic Algorithm
Introduction 1m Outline 1m Non-Propagation Supervised Learning 3m Optimization Problems 4m Search Space 1m Genetic Algorithm 2m Genetic Algorithm Flowchart 1m Population 3m Encoding 4m Fitness Function 2m Selection 3m Crossover 4m Mutation 4m Encoding Genome Using ENCOG 2m Population Using ENCOG 2m Fitness Function Using ENCOG 1m Genetic Trainer Using ENCOG 1m Crossover Operators Using ENCOG 3m Mutation Operators Using ENCOG 1m Genetic Algorithm Training Using ENCOG 1m Demo: Traveling Salesman Problem - Setup 7m Demo: Traveling Salesman Problem - Population 3m Demo: Traveling Salesman Problem - Fitness Function 2m Demo: Traveling Salesman Problem - Genetic Trainer 1m Demo: Traveling Salesman Problem - Iterations 3m Applications of Genetic Algorithm 1m Summary 2m
Course Summary
Course Summary 4m References and Resources 1m Future Roadmap 1m
Description
Course info
Rating
(56)
Level
Advanced
Updated
Mar 24, 2014
Duration
3h 41m
Your 10-day individual free trial includes:

Expanded library

This course and over 7,000+ additional courses from our full course library.

Hands-on library

Practice and apply knowledge faster in real-world scenarios with projects and interactive courses.
*Available on Premium only
Start a Premium 10-day free trial
Description

Finding patterns in a multidimensional dataset has always been a challenging task, but self-organizing maps can simplify this process and can help to find interesting patterns and inferences. In this course, you will learn not only the fundamentals of self-organizing maps but also the implementation in a C# application using the ENCOG machine learning framework. In this course, you will also learn to use Hopfield networks in a pattern recall and reconstruction application. This course will also provide a real world case study on time series forecasting, where you will learn to forecast future behavior using historical values. The course also covers another very important aspect of machine learning: optimization. You will learn to solve optimization problems with the help of genetic algorithms. The concepts learned in this course are applicable for developers working in any other framework in any other language.

About the author
Abhishek Kumar
About the author

Abhishek Kumar is a data science consultant, author, and Google Developers Expert (GDE) in machine learning. He holds a master’s degree from the University of California, Berkeley, and has been featured in the "Top 40 under 40 Data Scientist" list.

More from the author
Building Machine Learning Solutions with TensorFlow.js
Intermediate
4h 7m
Dec 2, 2020
Building End-to-end Machine Learning Workflows with Kubeflow
Beginner
3h 32m
Apr 24, 2020
Doing Data Science with Python
Beginner
6h 24m
Dec 28, 2017
More courses by Abhishek Kumar

You're the smartest person in the room

PROVE IT

Your team won't just close the skills gap

THEY'LL HURDLE IT

Course info
Rating
(56)
Level
Advanced
Updated
Mar 24, 2014
Duration
3h 41m
Pluralsight IQ
Know exactly where everyone on your team stands with assessments and analytics.
Try our full library including this course free for your whole team for 14-days.