College Level Neural Nets [I] – Basic Nets: Math & Practice!

Course Curriculum

Chapter 1: Introduction To Machine Learning

Lecture 1: Promo Video

Lecture 2: Introduction To Machine Learning

Chapter 2: The Linear Perceptron

Lecture 1: Introduction To The Classification Problem

Lecture 2: A Simple Glimpse Of Overfitting

Lecture 3: The Perceptron Equation

Lecture 4: Visualization Of The Perceptron Equation

Lecture 5: Proof : Weight Vector Is Perpendicular To The Decision Boundary

Lecture 6: More Visualization For The Perceptron Weights – I

Lecture 7: More Visualization Of The Perceptron Weights – II

Lecture 8: Activation Functions

Lecture 9: Graphical Representation Of A Neural Network

Lecture 10: Types Of Machine Learning

Lecture 11: Solved Example (I) : Single Layer Perceptron Designed Graphically

Chapter 3: Non-Linearly Separable Data And The Multi Layer Perceptron (MLP)

Lecture 1: Introduction To Multi-Layer Perceptrons

Lecture 2: Solved Example (II) : MLP Design Graphically

Lecture 3: Intuition Of Multi-Layer Perceptrons – Part 1

Lecture 4: Intuition Of Multi-Layer Perceptrons – Part 2

Lecture 5: The XOR Problem – Part 1

Lecture 6: The XOR Problem – Part 2

Lecture 7: MultiClass Classification And The Sigmoid Activation

Lecture 8: Vectorized Notation And The Weight Matrix

Chapter 4: Perceptron Learning !

Lecture 1: The Perceptron Learning Rule – Part 1

Lecture 2: The Perceptron Learning Rule – Part 2

Lecture 3: Proof : Perceptron Convergence Theorem – Part 1

Lecture 4: Proof : Perceptron Convergence Theorem – Part 2

Lecture 5: Proof : Perceptron Convergence Theorem – Part 3

Lecture 6: Three Main Problems Of The Threshold Perceptron

Chapter 5: The Gradient Descent Algorithm

Lecture 1: The Error Function

Lecture 2: The Sigmoid Activation Function Again

Lecture 3: Deriving The Gradient Descent Algorithm

Lecture 4: Notes About Gradient Descent

Lecture 5: More Notes And filling Up

Lecture 6: Solved Example (III) : Gradient Descent Convergence

Lecture 7: Solved Example (IIII) : MLP With Linear Activations

Chapter 6: The Back-Propagation Algorithm !

Lecture 1: Derivation Of Back Propagation – Part 1

Lecture 2: Derivation Of Back Propagation – Part 2

Lecture 3: Derivation Of Back Propagation – Part 3

Lecture 4: Vectorization Of BackPropagation – Part 1

Lecture 5: Vectorization Of BackPropagation – Part 2

Lecture 6: Vectorization Of BackPropagation – Part 3

Lecture 7: Vectorization Of BackPropagation – Part 4

Lecture 8: Vectorization Of BackPropagation – Part 5 – Batch Vectorization

Chapter 7: Regularization !

Lecture 1: Regression, Overfitting, And Underfitting

Lecture 2: Introduction To Reglarization

Lecture 3: Different Ways For Regularization

Lecture 4: L1 vs L2 Regularization – Part 1 – Gradient Descent

Lecture 5: L1 vs L2 Regularization -Part 2 – Numerical, Intuitive, And Graphical Comparison

Lecture 6: Dropout ! – Intuition

Lecture 7: Dropout vs Inverted Dropout

Lecture 8: Dropout in a nutshell

Lecture 9: Cross-Validation : How Do I Know I Am Overfitting Or Underfitting ?

Chapter 8: Model Performance Metrics !

Lecture 1: Class Imbalance – Why Is Accuracy Not Always The Best Metric ?

Lecture 2: Precision – Recall , And F1 Score

Lecture 3: F1 Score vs Simple Average

Lecture 4: Precision-Recall Curve

Lecture 5: ROC and AUC

Chapter 9: Improving Neural Network Performance – Part (I)

Lecture 1: Gradient Descent With Momentum – Part 1

Lecture 2: Gradient Descent With Momentum – Part 2

Lecture 3: Adagrad And RMSProb

Lecture 4: Adam And Learning Rate Decay

Lecture 5: The Vanishing Gradient Problem

Lecture 6: Input Centering And Normalization – Part 1

Lecture 7: Input Centering And Normalization – Part 2

Lecture 8: Weight Initialization – Part 1 – The Symmetry Problem

Lecture 9: Weight Initialization – Part 2

Lecture 10: Changing Activation Functions – Tanh – Relu – LeakyRelu

Chapter 10: Maximum Likelihood Estimation Review

Lecture 1: Source Of Those Lectures

Lecture 2: Maximum Likelihood Estimation – Quick Overview

Lecture 3: Maximum Likelihood Estimation Of Gaussian Distribution Parameters

Chapter 11: Improving Neural Network Performance – Part (II)

Lecture 1: The Sigmoid And Bernoulli Distribution

Lecture 2: The Cross Entropy Cost Function – Derivation

Lecture 3: The Cross Entropy & The Vanishing Gradient Problem

Lecture 4: Cross Entropy In Multi-Class Problems

Lecture 5: The Softmax Activation Function

Lecture 6: BackPropagation Derivation For The Softmax Activation Function

Lecture 7: Notes About Softmax

Chapter 12: Batch Normalization !

Lecture 1: Introduction To Batch Normalization – Part 1

Lecture 2: Introduction To Batch Normalization – Part 2

Lecture 3: Forward Pass Equations For Batch Normalization

Lecture 4: Batch Normalization :: Inference

Lecture 5: Derivation Of Back Propagation Through Batch Normalization – Part (I)

Lecture 6: Derivation Of Back Propagation Though Batch Normalization – Part 2

Chapter 13: Get My Other Courses !

Lecture 1: Get My Other Courses !