Machine Learning with Javascript

Focused View

Stephen Grider

17:39:16

61 View

01 - What is Machine Learning

001 Getting Started - How to Get Help.mp4

00:57

002 Course Resources.html

002 diagrams.zip

003 Join Our Community!.html

004 Solving Machine Learning Problems.mp4

06:04

005 A Complete Walkthrough.mp4

09:53

006 App Setup.mp4

02:01

007 Problem Outline.mp4

02:53

008 Identifying Relevant Data.mp4

04:11

009 Dataset Structures.mp4

05:47

010 Recording Observation Data.mp4

03:59

011 What Type of Problem.mp4

04:35

02 - Algorithm Overview

001 How K-Nearest Neighbor Works.mp4

08:23

002 Lodash Review.mp4

09:56

003 Implementing KNN.mp4

07:16

004 Finishing KNN Implementation.mp4

05:53

005 Testing the Algorithm.mp4

04:47

006 Interpreting Bad Results.mp4

04:12

007 Test and Training Data.mp4

04:05

008 Randomizing Test Data.mp4

03:48

009 Generalizing KNN.mp4

03:41

010 Gauging Accuracy.mp4

05:18

011 Printing a Report.mp4

03:29

012 Refactoring Accuracy Reporting.mp4

05:13

013 Investigating Optimal K Values.mp4

11:38

014 Updating KNN for Multiple Features.mp4

06:36

015 Multi-Dimensional KNN.mp4

03:56

016 N-Dimension Distance.mp4

09:50

017 Arbitrary Feature Spaces.mp4

08:27

018 Magnitude Offsets in Features.mp4

05:36

019 Feature Normalization.mp4

07:32

020 Normalization with MinMax.mp4

07:14

021 Applying Normalization.mp4

04:22

022 Feature Selection with KNN.mp4

07:47

023 Objective Feature Picking.mp4

06:10

024 Evaluating Different Feature Values.mp4

02:53

03 - Onwards to Tensorflow JS!

001 Lets Get Our Bearings.mp4

07:27

002 A Plan to Move Forward.mp4

04:31

003 Tensor Shape and Dimension.mp4

12:04

004 Elementwise Operations.mp4

08:18

005 Broadcasting Operations.mp4

06:47

006 Logging Tensor Data.mp4

03:47

007 Tensor Accessors.mp4

05:24

008 Creating Slices of Data.mp4

07:46

009 Tensor Concatenation.mp4

05:28

010 Summing Values Along an Axis.mp4

05:13

011 Massaging Dimensions with ExpandDims.mp4

07:47

04 - Applications of Tensorflow

001 KNN with Regression.mp4

04:56

002 A Change in Data Structure.mp4

04:04

003 KNN with Tensorflow.mp4

09:18

004 Maintaining Order Relationships.mp4

06:30

005 Sorting Tensors.mp4

08:00

006 Averaging Top Values.mp4

07:43

007 Moving to the Editor.mp4

03:26

008 Loading CSV Data.mp4

10:10

009 Running an Analysis.mp4

06:10

010 Reporting Error Percentages.mp4

06:26

011 Normalization or Standardization.mp4

07:33

012 Numerical Standardization with Tensorflow.mp4

07:37

013 Applying Standardization.mp4

04:01

014 Debugging Calculations.mp4

08:14

015 What Now.mp4

04:00

05 - Getting Started with Gradient Descent

001 Linear Regression.mp4

02:39

002 Why Linear Regression.mp4

04:52

003 Understanding Gradient Descent.mp4

13:04

004 Guessing Coefficients with MSE.mp4

10:19

005 Observations Around MSE.mp4

05:56

006 Derivatives!.mp4

07:12

007 Gradient Descent in Action.mp4

11:46

008 Quick Breather and Review.mp4

05:46

009 Why a Learning Rate.mp4

17:05

010 Answering Common Questions.mp4

03:48

011 Gradient Descent with Multiple Terms.mp4

04:43

012 Multiple Terms in Action.mp4

10:39

06 - Gradient Descent with Tensorflow

001 Project Overview.mp4

06:01

002 Data Loading.mp4

05:17

003 Default Algorithm Options.mp4

08:32

004 Formulating the Training Loop.mp4

03:18

005 Initial Gradient Descent Implementation.mp4

09:24

006 Calculating MSE Slopes.mp4

06:52

007 Updating Coefficients.mp4

03:11

008 Interpreting Results.mp4

10:07

009 Matrix Multiplication.mp4

07:09

010 More on Matrix Multiplication.mp4

06:40

011 Matrix Form of Slope Equations.mp4

06:21

012 Simplification with Matrix Multiplication.mp4

09:28

013 How it All Works Together!.mp4

14:01

07 - Increasing Performance with Vectorized Solutions

001 Refactoring the Linear Regression Class.mp4

07:40

002 Refactoring to One Equation.mp4

08:58

003 A Few More Changes.mp4

06:13

004 Same Results Or Not.mp4

03:19

005 Calculating Model Accuracy.mp4

08:37

006 Implementing Coefficient of Determination.mp4

07:44

007 Dealing with Bad Accuracy.mp4

07:47

008 Reminder on Standardization.mp4

04:36

009 Data Processing in a Helper Method.mp4

03:38

010 Reapplying Standardization.mp4

05:57

011 Fixing Standardization Issues.mp4

05:36

012 Massaging Learning Rates.mp4

03:15

013 Moving Towards Multivariate Regression.mp4

11:44

014 Refactoring for Multivariate Analysis.mp4

07:28

015 Learning Rate Optimization.mp4

08:04

016 Recording MSE History.mp4

05:21

017 Updating Learning Rate.mp4

06:41

08 - Plotting Data with Javascript

001 Observing Changing Learning Rate and MSE.mp4

04:17

002 Plotting MSE Values.mp4

05:21

003 Plotting MSE History against B Values.mp4

04:22

09 - Gradient Descent Alterations

001 Batch and Stochastic Gradient Descent.mp4

07:17

002 Refactoring Towards Batch Gradient Descent.mp4

05:06

003 Determining Batch Size and Quantity.mp4

06:02

004 Iterating Over Batches.mp4

07:48

005 Evaluating Batch Gradient Descent Results.mp4

05:41

006 Making Predictions with the Model.mp4

07:37

10 - Natural Binary Classification

001 Introducing Logistic Regression.mp4

02:27

002 Logistic Regression in Action.mp4

06:31

003 Bad Equation Fits.mp4

05:31

004 The Sigmoid Equation.mp4

04:31

005 Decision Boundaries.mp4

07:47

006 Changes for Logistic Regression.mp4

01:11

007 Project Setup for Logistic Regression.mp4

05:51

008 Project Download.html

008 regressions.zip

009 Importing Vehicle Data.mp4

04:27

010 Encoding Label Values.mp4

04:18

011 Updating Linear Regression for Logistic Regression.mp4

07:08

012 The Sigmoid Equation with Logistic Regression.mp4

04:27

013 A Touch More Refactoring.mp4

07:46

014 Gauging Classification Accuracy.mp4

03:27

015 Implementing a Test Function.mp4

05:16

016 Variable Decision Boundaries.mp4

07:16

017 Mean Squared Error vs Cross Entropy.mp4

05:46

018 Refactoring with Cross Entropy.mp4

05:08

019 Finishing the Cost Refactor.mp4

04:36

020 Plotting Changing Cost History.mp4

03:24

11 - Multi-Value Classification

001 Multinominal Logistic Regression.mp4

02:19

002 A Smart Refactor to Multinominal Analysis.mp4

05:07

003 A Smarter Refactor!.mp4

03:45

004 A Single Instance Approach.mp4

09:50

005 Refactoring to Multi-Column Weights.mp4

04:39

006 A Problem to Test Multinominal Classification.mp4

04:37

007 Classifying Continuous Values.mp4

04:41

008 Training a Multinominal Model.mp4

06:19

009 Marginal vs Conditional Probability.mp4

09:56

010 Sigmoid vs Softmax.mp4

06:08

011 Refactoring Sigmoid to Softmax.mp4

04:42

012 Implementing Accuracy Gauges.mp4

02:36

013 Calculating Accuracy.mp4

03:15

12 - Image Recognition In Action

001 Handwriting Recognition.mp4

02:10

002 Greyscale Values.mp4

05:11

003 Many Features.mp4

03:29

004 Flattening Image Data.mp4

06:06

005 Encoding Label Values.mp4

05:44

006 Implementing an Accuracy Gauge.mp4

07:26

007 Unchanging Accuracy.mp4

01:55

008 Debugging the Calculation Process.mp4

08:12

009 Dealing with Zero Variances.mp4

06:15

010 Backfilling Variance.mp4

02:36

13 - Performance Optimization

001 Handing Large Datasets.mp4

04:14

002 Minimizing Memory Usage.mp4

04:50

003 Creating Memory Snapshots.mp4

05:14

004 The Javascript Garbage Collector.mp4

06:49

005 Shallow vs Retained Memory Usage.mp4

05:50

006 Measuring Memory Usage.mp4

08:29

007 Releasing References.mp4

03:14

008 Measuring Footprint Reduction.mp4

03:50

009 Optimization Tensorflow Memory Usage.mp4

01:31

010 Tensorflows Eager Memory Usage.mp4

04:40

011 Cleaning up Tensors with Tidy.mp4

02:48

012 Implementing TF Tidy.mp4

03:31

013 Tidying the Training Loop.mp4

03:57

014 Measuring Reduced Memory Usage.mp4

01:34

015 One More Optimization.mp4

02:35

016 Final Memory Report.mp4

02:44

017 Plotting Cost History.mp4

04:03

018 NaN in Cost History.mp4

04:18

019 Fixing Cost History.mp4

04:46

020 Massaging Learning Parameters.mp4

01:40

021 Improving Model Accuracy.mp4

04:27

14 - Appendix Custom CSV Loader

001 Loading CSV Files.mp4

02:06

002 A Test Dataset.mp4

02:00

003 Reading Files from Disk.mp4

03:08

004 Splitting into Columns.mp4

02:54

005 Dropping Trailing Columns.mp4

02:30

006 Parsing Number Values.mp4

03:36

007 Custom Value Parsing.mp4

04:19

008 Extracting Data Columns.mp4

05:35

009 Shuffling Data via Seed Phrase.mp4

05:13

010 Splitting Test and Training.mp4

07:44

15 - Extras

001 Bonus!.html

Description

Master Machine Learning from scratch using Javascript and TensorflowJS with hands-on projects.

What You'll Learn?

Assemble machine learning algorithms from scratch!
Build interesting applications using Javascript and ML techniques
Understand how ML works without relying on mysterious libraries
Optimize your algorithms with advanced performance and memory usage profiling
Use the low-level features of Tensorflow JS to supercharge your algorithms
Grow a strong intuition of ML best practices

Who is this for?

Javascript developers interested in Machine Learning

What You Need to Know?

Basic understanding of terminal and command line usage

Ability to read basic math equations

More details

Description
If you're here, you already know the truth: Machine Learning is the future of everything.
In the coming years, there won't be a single industry in the world untouched by Machine Learning.Â A transformative force, you can either choose to understand it now, or lose out on a wave of incredible change.Â You probably already use apps many times each day that rely upon Machine Learning techniques.Â So why stay in the dark any longer?
There are many courses on Machine Learning already available.Â IÂ built this course to be the best introduction to the topic.Â No subject is left untouched, and we never leave any area in the dark.Â If you take this course, you will be prepared to enter and understand any sub-discipline in the world of Machine Learning.

A common question - Why Javascript?Â I thought MLÂ was all about Python and R?
The answer is simple - ML with Javascript is just plain easier to learn than with Python.Â Although it is immensely popular, Python is an 'expressive' language, which is a code-word that means 'a confusing language'.Â A single line of Python can contain a tremendous amount of functionality; this is great when you understand the language and the subject matter, but not so much when you're trying to learn a brand new topic.
Besides Javascript making ML easier to understand, it also opens new horizons for apps that you can build.Â Rather than being limited to deploying Python code on the server for running your MLÂ code, you can build single-page apps, or even browser extensions that run interesting algorithms, which can give you the possibility of developing a completely novel use case!

Does this course focus on algorithms, or math, or Tensorflow, or what?!?!
Let's be honest - the vast majority of ML courses available online dance around the confusing topics.Â They encourage you to use pre-build algorithms and functions that do all the heavy lifting for you.Â Although this can lead you to quick successes, in the end it will hamper your ability to understand ML.Â You can only understand how to apply MLÂ techniques if you understand the underlying algorithms.
That's the goal of this course - I want you to understand the exact math and programming techniques that are used in the most common ML algorithms.Â Once you have this knowledge, you can easily pick up new algorithms on the fly, and build far more interesting projects and applications than other engineers who only understand how to hand data to a magic library.
Don't have a background in math?Â That's OK! I take special care to make sure that no lecture gets too far into 'mathy' topics without giving a proper introduction to what is going on.

A short list of what you will learn:
Advanced memory profiling to enhance the performance of your algorithms
Build apps powered by the powerful Tensorflow JSÂ library
Develop programs that work either in the browser or with Node JS
Write clean, easy to understand MLÂ code, no one-name variables or confusing functions
Pick up the basics of Linear Algebra so you can dramatically speed up your code with matrix-based operations. (Don't worry, I'll make the math easy!)
Comprehend how to twist common algorithms to fit your unique use cases
Plot the results of your analysis using a custom-build graphing library
Learn performance-enhancing strategies that can be applied to any type of Javascript code
Data loading techniques, both in the browser and Node JSÂ environments
Who this course is for:
Javascript developers interested in Machine Learning

User Reviews

Rating

average 0

Total votes0

Focused display

Stephen Grider has been building complex Javascript front ends for top corporations in the San Francisco Bay Area. With an innate ability to simplify complex topics, Stephen has been mentoring engineers beginning their careers in software development for years, and has now expanded that experience onto Udemy, authoring the highest rated React course. He teaches on Udemy to share the knowledge he has gained with other software engineers. Invest in yourself by learning from Stephen's published courses.

Udemy

View courses Udemy

Students take courses primarily to improve job-related skills.Some courses generate credit toward technical certification. Udemy has made a special effort to attract corporate trainers seeking to create coursework for employees of their company.