CF

Machine Learning with Javascript

17h 42m 20s
English
Paid

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.  A transformative force, you can either choose to understand it now, or lose out on a wave of incredible change.  You probably already use apps many times each day that rely upon Machine Learning techniques.  So why stay in the dark any longer?

There are many courses on Machine Learning already available.  I built this course to be the bestintroduction to the topic.  No subject is left untouched, and we never leave any area in the dark.  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?  I thought ML was all about Python and R?

The answer is simple - ML with Javascript is just plain easier to learn than with Python.  Although it is immensely popular, Python is an 'expressive' language, which is a code-word that means 'a confusing language'.  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.  Rather than being limited to deploying Python code on the server for running your ML 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.  They encourage you to use pre-build algorithms and functions that do all the heavy lifting for you.  Although this can lead you to quick successes, in the end it will hamper your ability to understand ML.  You can only understand how to apply ML 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.  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?  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 JS library

  • Develop programs that work either in the browser or with Node JS

  • Write clean, easy to understand ML 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 JS environments

Requirements:
  • Basic understanding of terminal and command line usage
  • Ability to read basic math equations
Who this course is for:
  • Javascript developers interested in Machine Learning

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

About the Authors

Stephen Grider

Stephen Grider thumbnail

Stephen Grider is one of the longest-running and most prolific instructors on Udemy, with a catalog covering essentially every major JavaScript framework, plus Docker, Kubernetes, AWS, and the broader full-stack development landscape. His teaching style is patient and project-oriented — most of his courses are structured around building a substantial application from scratch rather than working through disconnected tutorial examples.

The catalog covers React, Redux, Next.js, Vue, Angular, GraphQL, Node.js, Docker / Kubernetes, AWS infrastructure, React Native and Flutter for mobile, the algorithm / data-structure interview prep track, and the modern TypeScript / Bun / Rust adjacent material that working JavaScript developers increasingly encounter. Few independent instructors have maintained Stephen's breadth this consistently for this long.

The CourseFlix listing under this source carries over 25 Stephen Grider courses spanning that range. Material is paid; Stephen Grider courses are typically sold individually on Udemy. Courses are aimed primarily at developers picking up a specific technology through working through a complete project.

Udemy

Udemy thumbnail

Udemy is the largest open marketplace for online courses on the internet. Founded in 2010 by Eren Bali, Oktay Caglar, and Gagan Biyani and headquartered in San Francisco, the company went public on the Nasdaq in 2021 under the ticker UDMY. The platform hosts well over two hundred thousand courses across software development, IT and cloud, data science, design, business, marketing, and creative skills, taught by tens of thousands of independent instructors. Roughly seventy million learners use it worldwide, and the corporate arm — Udemy Business — supplies a curated subset of that catalog to enterprise customers.

Because Udemy is a marketplace rather than a single editorial publisher, the catalog is uneven by design. The strongest material lives in the long-form, project-based courses authored by working engineers — full-stack JavaScript, React, Node.js, Python data science, AWS, Docker and Kubernetes, mobile development with Flutter and React Native, and cloud certification preparation. The CourseFlix listing under this source is the slice of that catalog that has been mirrored here for offline-friendly viewing, organized by topic and updated as new releases land. Pricing on Udemy itself swings dramatically with the site's near-permanent sales, which is why the platform is best treated as a deep reference catalog: pick instructors with strong reviews and a track record of updating their material rather than buying on the headline price alone.

Watch Online 183 lessons

This is a demo lesson (10:00 remaining)

You can watch up to 10 minutes for free. Subscribe to unlock all 183 lessons in this course and access 10,000+ hours of premium content across all courses.

View Pricing
0:00
/
#1: Getting Started - How to Get Help
All Course Lessons (183)
#Lesson TitleDurationAccess
1
Getting Started - How to Get Help Demo
00:58
2
Solving Machine Learning Problems
06:05
3
A Complete Walkthrough
09:54
4
App Setup
02:02
5
Problem Outline
02:54
6
Identifying Relevant Data
04:12
7
Dataset Structures
05:48
8
Recording Observation Data
04:00
9
What Type of Problem?
04:36
10
How K-Nearest Neighbor Works
08:24
11
Lodash Review
09:57
12
Implementing KNN
07:17
13
Finishing KNN Implementation
05:54
14
Testing the Algorithm
04:49
15
Interpreting Bad Results
04:13
16
Test and Training Data
04:06
17
Randomizing Test Data
03:49
18
Generalizing KNN
03:42
19
Gauging Accuracy
05:19
20
Printing a Report
03:30
21
Refactoring Accuracy Reporting
05:14
22
Investigating Optimal K Values
11:39
23
Updating KNN for Multiple Features
06:37
24
Multi-Dimensional KNN
03:57
25
N-Dimension Distance
09:51
26
Arbitrary Feature Spaces
08:28
27
Magnitude Offsets in Features
05:37
28
Feature Normalization
07:33
29
Normalization with MinMax
07:15
30
Applying Normalization
04:23
31
Feature Selection with KNN
07:48
32
Objective Feature Picking
06:11
33
Evaluating Different Feature Values
02:54
34
Let's Get Our Bearings
07:28
35
A Plan to Move Forward
04:32
36
Tensor Shape and Dimension
12:05
37
Elementwise Operations
08:19
38
Broadcasting Operations
06:48
39
Logging Tensor Data
03:48
40
Tensor Accessors
05:25
41
Creating Slices of Data
07:47
42
Tensor Concatenation
05:29
43
Summing Values Along an Axis
05:14
44
Massaging Dimensions with ExpandDims
07:48
45
KNN with Regression
04:57
46
A Change in Data Structure
04:05
47
KNN with Tensorflow
09:19
48
Maintaining Order Relationships
06:31
49
Sorting Tensors
08:01
50
Averaging Top Values
07:44
51
Moving to the Editor
03:27
52
Loading CSV Data
10:11
53
Running an Analysis
06:11
54
Reporting Error Percentages
06:27
55
Normalization or Standardization?
07:34
56
Numerical Standardization with Tensorflow
07:38
57
Applying Standardization
04:02
58
Debugging Calculations
08:15
59
What Now?
04:01
60
Linear Regression
02:40
61
Why Linear Regression?
04:53
62
Understanding Gradient Descent
13:05
63
Guessing Coefficients with MSE
10:20
64
Observations Around MSE
05:57
65
Derivatives!
07:13
66
Gradient Descent in Action
11:47
67
Quick Breather and Review
05:47
68
Why a Learning Rate?
17:06
69
Answering Common Questions
03:49
70
Gradient Descent with Multiple Terms
04:44
71
Multiple Terms in Action
10:40
72
Project Overview
06:02
73
Data Loading
05:18
74
Default Algorithm Options
08:33
75
Formulating the Training Loop
03:19
76
Initial Gradient Descent Implementation
09:25
77
Calculating MSE Slopes
06:53
78
Updating Coefficients
03:12
79
Interpreting Results
10:08
80
Matrix Multiplication
07:10
81
More on Matrix Multiplication
06:41
82
Matrix Form of Slope Equations
06:22
83
Simplification with Matrix Multiplication
09:29
84
How it All Works Together!
14:02
85
Refactoring the Linear Regression Class
07:41
86
Refactoring to One Equation
08:59
87
A Few More Changes
06:14
88
Same Results? Or Not?
03:20
89
Calculating Model Accuracy
08:38
90
Implementing Coefficient of Determination
07:45
91
Dealing with Bad Accuracy
07:48
92
Reminder on Standardization
04:37
93
Data Processing in a Helper Method
03:39
94
Reapplying Standardization
05:58
95
Fixing Standardization Issues
05:37
96
Massaging Learning Rates
03:16
97
Moving Towards Multivariate Regression
11:45
98
Refactoring for Multivariate Analysis
07:29
99
Learning Rate Optimization
08:05
100
Recording MSE History
05:22
101
Updating Learning Rate
06:42
102
Observing Changing Learning Rate and MSE
04:18
103
Plotting MSE Values
05:22
104
Plotting MSE History against B Values
04:23
105
Batch and Stochastic Gradient Descent
07:18
106
Refactoring Towards Batch Gradient Descent
05:07
107
Determining Batch Size and Quantity
06:03
108
Iterating Over Batches
07:49
109
Evaluating Batch Gradient Descent Results
05:42
110
Making Predictions with the Model
07:38
111
Introducing Logistic Regression
02:28
112
Logistic Regression in Action
06:32
113
Bad Equation Fits
05:32
114
The Sigmoid Equation
04:32
115
Decision Boundaries
07:48
116
Changes for Logistic Regression
01:12
117
Project Setup for Logistic Regression
05:52
118
Importing Vehicle Data
04:28
119
Encoding Label Values
04:19
120
Updating Linear Regression for Logistic Regression
07:09
121
The Sigmoid Equation with Logistic Regression
04:28
122
A Touch More Refactoring
07:47
123
Gauging Classification Accuracy
03:28
124
Implementing a Test Function
05:17
125
Variable Decision Boundaries
07:17
126
Mean Squared Error vs Cross Entropy
05:47
127
Refactoring with Cross Entropy
05:09
128
Finishing the Cost Refactor
04:37
129
Plotting Changing Cost History
03:25
130
Multinominal Logistic Regression
02:20
131
A Smart Refactor to Multinominal Analysis
05:08
132
A Smarter Refactor!
03:46
133
A Single Instance Approach
09:51
134
Refactoring to Multi-Column Weights
04:40
135
A Problem to Test Multinominal Classification
04:38
136
Classifying Continuous Values
04:42
137
Training a Multinominal Model
06:20
138
Marginal vs Conditional Probability
09:57
139
Sigmoid vs Softmax
06:09
140
Refactoring Sigmoid to Softmax
04:43
141
Implementing Accuracy Gauges
02:37
142
Calculating Accuracy
03:16
143
Handwriting Recognition
02:11
144
Greyscale Values
05:12
145
Many Features
03:30
146
Flattening Image Data
06:07
147
Encoding Label Values
05:45
148
Implementing an Accuracy Gauge
07:27
149
Unchanging Accuracy
01:56
150
Debugging the Calculation Process
08:13
151
Dealing with Zero Variances
06:16
152
Backfilling Variance
02:37
153
Handing Large Datasets
04:15
154
Minimizing Memory Usage
04:51
155
Creating Memory Snapshots
05:15
156
The Javascript Garbage Collector
06:50
157
Shallow vs Retained Memory Usage
05:51
158
Measuring Memory Usage
08:30
159
Releasing References
03:15
160
Measuring Footprint Reduction
03:51
161
Optimization Tensorflow Memory Usage
01:32
162
Tensorflow's Eager Memory Usage
04:41
163
Cleaning up Tensors with Tidy
02:49
164
Implementing TF Tidy
03:32
165
Tidying the Training Loop
03:58
166
Measuring Reduced Memory Usage
01:35
167
One More Optimization
02:36
168
Final Memory Report
02:45
169
Plotting Cost History
04:04
170
NaN in Cost History
04:19
171
Fixing Cost History
04:47
172
Massaging Learning Parameters
01:41
173
Improving Model Accuracy
04:28
174
Loading CSV Files
02:07
175
A Test Dataset
02:01
176
Reading Files from Disk
03:09
177
Splitting into Columns
02:55
178
Dropping Trailing Columns
02:31
179
Parsing Number Values
03:37
180
Custom Value Parsing
04:20
181
Extracting Data Columns
05:36
182
Shuffling Data via Seed Phrase
05:14
183
Splitting Test and Training
07:45
Unlock unlimited learning

Get instant access to all 182 lessons in this course, plus thousands of other premium courses. One subscription, unlimited knowledge.

Learn more about subscription

Related courses

Frequently asked questions

What is Machine Learning with Javascript about?
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. A transformative force, you can either choose to…
Who teaches this course?
It is taught by Stephen Grider, Udemy. You can find more courses by these instructors on the corresponding source pages.
How long is the course?
It contains 183 lessons with a total runtime of 17 hours 42 minutes. Every lesson is available to watch online at your own pace.
Is it free to watch?
It is part of CourseFlix's premium catalog. A subscription unlocks the full video player; the course description, table of contents, and preview information are available to everyone.
Where can I watch it online?
The course is available to watch online on CourseFlix at https://courseflix.net/course/machine-learning-with-javascript. The page hosts every lesson with the integrated video player; no download is required.