English | MP4 | AVC 1280×720 | AAC 48KHz 2ch | 17.5 Hours | 10.0 GB
Master Machine Learning from scratch using Javascript and TensorflowJS with hands-on projects.
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 best introduction 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
Table of Contents
What is Machine Learning
1 Getting Started – How to Get Help
2 Solving Machine Learning Problems
3 A Complete Walkthrough
4 App Setup
5 Problem Outline
6 Identifying Relevant Data
7 Dataset Structures
8 Recording Observation Data
9 What Type of Problem
Algorithm Overview
10 How K-Nearest Neighbor Works
11 Lodash Review
12 Implementing KNN
13 Finishing KNN Implementation
14 Testing the Algorithm
15 Interpreting Bad Results
16 Test and Training Data
17 Randomizing Test Data
18 Generalizing KNN
19 Gauging Accuracy
20 Printing a Report
21 Refactoring Accuracy Reporting
22 Investigating Optimal K Values
23 Updating KNN for Multiple Features
24 Multi-Dimensional KNN
25 N-Dimension Distance
26 Arbitrary Feature Spaces
27 Magnitude Offsets in Features
28 Feature Normalization
29 Normalization with MinMax
30 Applying Normalization
31 Feature Selection with KNN
32 Objective Feature Picking
33 Evaluating Different Feature Values
Onwards to Tensorflow JS!
34 Let’s Get Our Bearings
35 A Plan to Move Forward
36 Tensor Shape and Dimension
37 Elementwise Operations
38 Broadcasting Operations
39 Logging Tensor Data
40 Tensor Accessors
41 Creating Slices of Data
42 Tensor Concatenation
43 Summing Values Along an Axis
44 Massaging Dimensions with ExpandDims
Applications of Tensorflow
45 KNN with Regression
46 A Change in Data Structure
47 KNN with Tensorflow
48 Maintaining Order Relationships
49 Sorting Tensors
50 Averaging Top Values
51 Moving to the Editor
52 Loading CSV Data
53 Running an Analysis
54 Reporting Error Percentages
55 Normalization or Standardization
56 Numerical Standardization with Tensorflow
57 Applying Standardization
58 Debugging Calculations
59 What Now
Getting Started with Gradient Descent
60 Linear Regression
61 Why Linear Regression
62 Understanding Gradient Descent
63 Guessing Coefficients with MSE
64 Observations Around MSE
65 Derivatives!
66 Gradient Descent in Action
67 Quick Breather and Review
68 Why a Learning Rate
69 Answering Common Questions
70 Gradient Descent with Multiple Terms
71 Multiple Terms in Action
Gradient Descent with Tensorflow
72 Project Overview
73 Data Loading
74 Default Algorithm Options
75 Formulating the Training Loop
76 Initial Gradient Descent Implementation
77 Calculating MSE Slopes
78 Updating Coefficients
79 Interpreting Results
80 Matrix Multiplication
81 More on Matrix Multiplication
82 Matrix Form of Slope Equations
83 Simplification with Matrix Multiplication
84 How it All Works Together!
Increasing Performance with Vectorized Solutions
85 Refactoring the Linear Regression Class
86 Refactoring to One Equation
87 A Few More Changes
88 Same Results Or Not
89 Calculating Model Accuracy
90 Implementing Coefficient of Determination
91 Dealing with Bad Accuracy
92 Reminder on Standardization
93 Data Processing in a Helper Method
94 Reapplying Standardization
95 Fixing Standardization Issues
96 Massaging Learning Rates
97 Moving Towards Multivariate Regression
98 Refactoring for Multivariate Analysis
99 Learning Rate Optimization
100 Recording MSE History
101 Updating Learning Rate
Plotting Data with Javascript
102 Observing Changing Learning Rate and MSE
103 Plotting MSE Values
104 Plotting MSE History against B Values
Gradient Descent Alterations
105 Batch and Stochastic Gradient Descent
106 Refactoring Towards Batch Gradient Descent
107 Determining Batch Size and Quantity
108 Iterating Over Batches
109 Evaluating Batch Gradient Descent Results
110 Making Predictions with the Model
Natural Binary Classification
111 Introducing Logistic Regression
112 Logistic Regression in Action
113 Bad Equation Fits
114 The Sigmoid Equation
115 Decision Boundaries
116 Changes for Logistic Regression
117 Project Setup for Logistic Regression
118 Project Download
119 Importing Vehicle Data
120 Encoding Label Values
121 Updating Linear Regression for Logistic Regression
122 The Sigmoid Equation with Logistic Regression
123 A Touch More Refactoring
124 Gauging Classification Accuracy
125 Implementing a Test Function
126 Variable Decision Boundaries
127 Mean Squared Error vs Cross Entropy
128 Refactoring with Cross Entropy
129 Finishing the Cost Refactor
130 Plotting Changing Cost History
Multi-Value Classification
131 Multinominal Logistic Regression
132 A Smart Refactor to Multinominal Analysis
133 A Smarter Refactor!
134 A Single Instance Approach
135 Refactoring to Multi-Column Weights
136 A Problem to Test Multinominal Classification
137 Classifying Continuous Values
138 Training a Multinominal Model
139 Marginal vs Conditional Probability
140 Sigmoid vs Softmax
141 Refactoring Sigmoid to Softmax
142 Implementing Accuracy Gauges
143 Calculating Accuracy
Image Recognition In Action
144 Handwriting Recognition
145 Greyscale Values
146 Many Features
147 Flattening Image Data
148 Encoding Label Values
149 Implementing an Accuracy Gauge
150 Unchanging Accuracy
151 Debugging the Calculation Process
152 Dealing with Zero Variances
153 Backfilling Variance
Performance Optimization
154 Handing Large Datasets
155 Minimizing Memory Usage
156 Creating Memory Snapshots
157 The Javascript Garbage Collector
158 Shallow vs Retained Memory Usage
159 Measuring Memory Usage
160 Releasing References
161 Measuring Footprint Reduction
162 Optimization Tensorflow Memory Usage
163 Tensorflow’s Eager Memory Usage
164 Cleaning up Tensors with Tidy
165 Implementing TF Tidy
166 Tidying the Training Loop
167 Measuring Reduced Memory Usage
168 One More Optimization
169 Final Memory Report
170 Plotting Cost History
171 NaN in Cost History
172 Fixing Cost History
173 Massaging Learning Parameters
174 Improving Model Accuracy
Appendix Custom CSV Loader
175 Loading CSV Files
176 A Test Dataset
177 Reading Files from Disk
178 Splitting into Columns
179 Dropping Trailing Columns
180 Parsing Number Values
181 Custom Value Parsing
182 Extracting Data Columns
183 Shuffling Data via Seed Phrase
184 Splitting Test and Training
Extras
185 Bonus!
Resolve the captcha to access the links!