Machine Learning with Javascript

سرفصل های دوره

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

01 - What is Machine Learning

001 Getting Started - How to Get Help

002 Course Resources.html

002 diagrams.zip

003 Join Our Community!.html

004 Solving Machine Learning Problems

005 A Complete Walkthrough

006 App Setup

007 Problem Outline

008 Identifying Relevant Data

009 Dataset Structures

010 Recording Observation Data

011 What Type of Problem

02 - Algorithm Overview

001 How K-Nearest Neighbor Works

002 Lodash Review

003 Implementing KNN

004 Finishing KNN Implementation

005 Testing the Algorithm

006 Interpreting Bad Results

007 Test and Training Data

008 Randomizing Test Data

009 Generalizing KNN

010 Gauging Accuracy

011 Printing a Report

012 Refactoring Accuracy Reporting

013 Investigating Optimal K Values

014 Updating KNN for Multiple Features

015 Multi-Dimensional KNN

016 N-Dimension Distance

017 Arbitrary Feature Spaces

018 Magnitude Offsets in Features

019 Feature Normalization

020 Normalization with MinMax

021 Applying Normalization

022 Feature Selection with KNN

023 Objective Feature Picking

024 Evaluating Different Feature Values

03 - Onwards to Tensorflow JS!

001 Lets Get Our Bearings

002 A Plan to Move Forward

003 Tensor Shape and Dimension

004 Elementwise Operations

005 Broadcasting Operations

006 Logging Tensor Data

007 Tensor Accessors

008 Creating Slices of Data

009 Tensor Concatenation

010 Summing Values Along an Axis

011 Massaging Dimensions with ExpandDims

04 - Applications of Tensorflow

001 KNN with Regression

002 A Change in Data Structure

003 KNN with Tensorflow

004 Maintaining Order Relationships

005 Sorting Tensors

006 Averaging Top Values

007 Moving to the Editor

008 Loading CSV Data

009 Running an Analysis

010 Reporting Error Percentages

011 Normalization or Standardization

012 Numerical Standardization with Tensorflow

013 Applying Standardization

014 Debugging Calculations

015 What Now

05 - Getting Started with Gradient Descent

001 Linear Regression

002 Why Linear Regression

003 Understanding Gradient Descent

004 Guessing Coefficients with MSE

005 Observations Around MSE

006 Derivatives!

007 Gradient Descent in Action

008 Quick Breather and Review

009 Why a Learning Rate

010 Answering Common Questions

011 Gradient Descent with Multiple Terms

012 Multiple Terms in Action

06 - Gradient Descent with Tensorflow

001 Project Overview

002 Data Loading

003 Default Algorithm Options

004 Formulating the Training Loop

005 Initial Gradient Descent Implementation

006 Calculating MSE Slopes

007 Updating Coefficients

008 Interpreting Results

009 Matrix Multiplication

010 More on Matrix Multiplication

011 Matrix Form of Slope Equations

012 Simplification with Matrix Multiplication

013 How it All Works Together!

07 - Increasing Performance with Vectorized Solutions

001 Refactoring the Linear Regression Class

002 Refactoring to One Equation

003 A Few More Changes

004 Same Results Or Not

005 Calculating Model Accuracy

006 Implementing Coefficient of Determination

007 Dealing with Bad Accuracy

008 Reminder on Standardization

009 Data Processing in a Helper Method

010 Reapplying Standardization

011 Fixing Standardization Issues

012 Massaging Learning Rates

013 Moving Towards Multivariate Regression

014 Refactoring for Multivariate Analysis

015 Learning Rate Optimization

016 Recording MSE History

017 Updating Learning Rate

08 - Plotting Data with Javascript

001 Observing Changing Learning Rate and MSE

002 Plotting MSE Values

003 Plotting MSE History against B Values

09 - Gradient Descent Alterations

001 Batch and Stochastic Gradient Descent

002 Refactoring Towards Batch Gradient Descent

003 Determining Batch Size and Quantity

004 Iterating Over Batches

005 Evaluating Batch Gradient Descent Results

006 Making Predictions with the Model

10 - Natural Binary Classification

001 Introducing Logistic Regression

002 Logistic Regression in Action

003 Bad Equation Fits

004 The Sigmoid Equation

005 Decision Boundaries

006 Changes for Logistic Regression

007 Project Setup for Logistic Regression

008 Project Download.html

008 regressions.zip

009 Importing Vehicle Data

010 Encoding Label Values

011 Updating Linear Regression for Logistic Regression

012 The Sigmoid Equation with Logistic Regression

013 A Touch More Refactoring

014 Gauging Classification Accuracy

015 Implementing a Test Function

016 Variable Decision Boundaries

017 Mean Squared Error vs Cross Entropy

018 Refactoring with Cross Entropy

019 Finishing the Cost Refactor

020 Plotting Changing Cost History

11 - Multi-Value Classification

001 Multinominal Logistic Regression

002 A Smart Refactor to Multinominal Analysis

003 A Smarter Refactor!

004 A Single Instance Approach

005 Refactoring to Multi-Column Weights

006 A Problem to Test Multinominal Classification

007 Classifying Continuous Values

008 Training a Multinominal Model

009 Marginal vs Conditional Probability

010 Sigmoid vs Softmax

011 Refactoring Sigmoid to Softmax

012 Implementing Accuracy Gauges

013 Calculating Accuracy

12 - Image Recognition In Action

001 Handwriting Recognition

002 Greyscale Values

003 Many Features

004 Flattening Image Data

005 Encoding Label Values

006 Implementing an Accuracy Gauge

007 Unchanging Accuracy

008 Debugging the Calculation Process

009 Dealing with Zero Variances

010 Backfilling Variance

13 - Performance Optimization

001 Handing Large Datasets

002 Minimizing Memory Usage

003 Creating Memory Snapshots

004 The Javascript Garbage Collector

005 Shallow vs Retained Memory Usage

006 Measuring Memory Usage

007 Releasing References

008 Measuring Footprint Reduction

009 Optimization Tensorflow Memory Usage

010 Tensorflows Eager Memory Usage

011 Cleaning up Tensors with Tidy

012 Implementing TF Tidy

013 Tidying the Training Loop

014 Measuring Reduced Memory Usage

015 One More Optimization

016 Final Memory Report

017 Plotting Cost History

018 NaN in Cost History

019 Fixing Cost History

020 Massaging Learning Parameters

021 Improving Model Accuracy

14 - Appendix Custom CSV Loader

001 Loading CSV Files

002 A Test Dataset

003 Reading Files from Disk

004 Splitting into Columns

005 Dropping Trailing Columns

006 Parsing Number Values

007 Custom Value Parsing

008 Extracting Data Columns

009 Shuffling Data via Seed Phrase

010 Splitting Test and Training

15 - Extras

001 Bonus!.html

189,000 تومان

افزودن به سبد خرید

خرید دانلودی فوری

در این روش نیاز به افزودن محصول به سبد خرید و تکمیل اطلاعات نیست و شما پس از وارد کردن ایمیل خود و طی کردن مراحل پرداخت لینک های دریافت محصولات را در ایمیل خود دریافت خواهید کرد.

تولید کننده: Udemy