College Level Neural Nets [I] Basic Nets- Math Practice!

College Level Neural Nets [I] – Basic Nets: Math & Practice!, available at $64.99, has an average rating of 4.65, with 83 lectures, based on 50 reviews, and has 831 subscribers.

You will learn about Step By Step Conceptual Introduction For Neural Networks And Deep Learning [Even If You Are A Beginner] Understanding The Basic Perceptron[Neuron] Conceptually, Graphically, And Mathematically – Perceptron Convergence Theorem Proof Mathematical Derivations For Deep Learning Modules Step-By-Step Derivation Of BackPropagation Algorithm Vectorization Of BackPropagation Different Performance Metrics Like Performance – Recall – F1 Score – ROC & AUC Mathematical Derivation Of Cross-Entropy Cost Function Mathematical Derivation Of Back-Propagation Through Batch-Normalization Different Solved Examples On Various Topics This course is ideal for individuals who are Deep Learning Engineers Or College Students Who Want To Gain Deep Mathematical Understanding Of The Topic It is particularly useful for Deep Learning Engineers Or College Students Who Want To Gain Deep Mathematical Understanding Of The Topic.

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

Summary

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

Price: $64.99

Average Rating: 4.65

Number of Lectures: 83

Number of Published Lectures: 83

Number of Curriculum Items: 83

Number of Published Curriculum Objects: 83

Original Price: $199.99

Quality Status: approved

Status: Live

What You Will Learn

Step By Step Conceptual Introduction For Neural Networks And Deep Learning [Even If You Are A Beginner]

Understanding The Basic Perceptron[Neuron] Conceptually, Graphically, And Mathematically – Perceptron Convergence Theorem Proof

Mathematical Derivations For Deep Learning Modules

Step-By-Step Derivation Of BackPropagation Algorithm

Vectorization Of BackPropagation

Different Performance Metrics Like Performance – Recall – F1 Score – ROC & AUC

Mathematical Derivation Of Cross-Entropy Cost Function

Mathematical Derivation Of Back-Propagation Through Batch-Normalization

Different Solved Examples On Various Topics

Who Should Attend

Deep Learning Engineers Or College Students Who Want To Gain Deep Mathematical Understanding Of The Topic

Target Audiences

Deep Learning Engineers Or College Students Who Want To Gain Deep Mathematical Understanding Of The Topic

Deep Learning is surely one of the hottest topics nowadays, with a tremendous amount of practical applications in many many fields.Those applications include, without being limited to, image classification, object detection, action recognition in videos, motion synthesis, machine translation, self-driving cars, speech recognition, speech and video generation, natural language processing and understanding, robotics, and many many more.

Now you might be wondering :

There is a very large number of courses well-explaining deep learning, why should I prefer this specific course over them ?

The answer is : You shouldn’t !Most of the other courses heavily focus on “Programming” deep learning applications as fast as possible, without giving detailed explanations on the underlying mathematical foundations that the field of deep learning was built upon. And this is exactly the gap that my course is designed to cover. It is designed to be used hand in hand with other programming courses, not to replace them.

Since this series is heavily mathematical, I will refer many many times during my explanations to sections from my own college level linear algebra course. In general, being quite familiar with linear algebra is a real prerequisite for this course.

Please have a look at the course syllables, and remember : This is only part (I) of the deep learning series!

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 !

Instructors

Ahmed Fathy, MSc
MSc, Senior Deep learning engineer @ Affectiva & Instructor

Rating Distribution

1 stars: 1 votes

2 stars: 1 votes

3 stars: 3 votes

4 stars: 11 votes

5 stars: 34 votes

Frequently Asked Questions

How long do I have access to the course materials?

You can view and review the lecture materials indefinitely, like an on-demand channel.

Can I take my courses with me wherever I go?

Definitely! If you have an internet connection, courses on Udemy are available on any device at any time. If you don’t have an internet connection, some instructors also let their students download course lectures. That’s up to the instructor though, so make sure you get on their good side!