Artificial Intelligence Masterclass

  1. Home
  2. Artificial-intelligence
  3. Artificial Intelligence Masterclass

Tags: Artificial Intelligence

Enter the new era of Hybrid AI Models optimized by Deep NeuroEvolution, with a complete toolkit of ML, DL & AI models

Last updated 2022-01-10 | 4.5

- How to Build an AI
- How to Build a Hybrid Intelligent System
- Fully-Connected Neural Networks

What you'll learn

How to Build an AI
How to Build a Hybrid Intelligent System
Fully-Connected Neural Networks
Convolutional Neural Networks
Recurrent Neural Networks
AutoEncoders
Variational AutoEncoders
Mixture Density Network
Deep Reinforcement Learning
Policy Gradient
Genetic Algorithms
Evolution Strategies
Covariance-Matrix Adaptation Evolution Strategies (CMA-ES)
Controllers
Meta Learning
Deep NeuroEvolution

* Requirements

* High school mathematics
* A bit of coding experience

Description

  • How to Build an AI
  • How to Build a Hybrid Intelligent System
  • Fully-Connected Neural Networks
  • Convolutional Neural Networks
  • Recurrent Neural Networks
  • AutoEncoders
  • Variational AutoEncoders
  • Mixture Density Network
  • Deep Reinforcement Learning
  • Policy Gradient
  • Genetic Algorithms
  • Evolution Strategies
  • Covariance-Matrix Adaptation Evolution Strategies (CMA-ES)
  • Controllers
  • Meta Learning
  • Deep NeuroEvolution

Course content

13 sections • 89 lectures

Introduction 6 lectures

Updates on Udemy Reviews Preview 01:09

Introduction + Course Structure + Demo Preview 16:44

BONUS: Learning Paths Preview 00:51

Your Three Best Resources Preview 10:42

Download the Resources here Preview 00:08

Meet your instructors! Preview 00:12

Step 1 - Artificial Neural Network 9 lectures

Welcome to Step 1 - Artificial Neural Network Preview 00:23

Plan of Attack Preview 02:51

The Neuron Preview 16:15

The Activation Function Preview 08:29

How do Neural Networks work? Preview 12:47

How do Neural Networks learn? Preview 12:58

Gradient Descent Preview 10:12

Stochastic Gradient Descent Preview 08:44

Backpropagation Preview 05:21

Step 2 - Convolutional Neural Network 10 lectures

Welcome to Step 2 - Convolutional Neural Network Preview 00:17

Plan of Attack Preview 03:31

What are Convolutional Neural Networks? Preview 15:49

Step 1 - The Convolution Operation Preview 16:38

Step 1 Bis - The ReLU Layer Preview 06:41

Step 2 - Pooling Preview 14:13

Step 3 - Flattening Preview 01:52

Step 4 - Full Connection Preview 19:24

Summary Preview 04:19

Softmax & Cross-Entropy Preview 18:20

Step 3 - AutoEncoder 11 lectures

Welcome to Step 3 - AutoEncoder Preview 00:16

Plan of Attack Preview 02:12

What are AutoEncoders? Preview 10:50

A Note on Biases Preview 01:15

Training an AutoEncoder Preview 06:10

Overcomplete Hidden Layers Preview 03:52

Sparse AutoEncoders Preview 06:15

Denoising AutoEncoders Preview 02:32

Contractive AutoEncoders Preview 02:23

Stacked AutoEncoders Preview 01:54

Deep AutoEncoders Preview 01:50

Step 4 - Variational AutoEncoder 4 lectures

Welcome to Step 4 - Variational AutoEncoder Preview 00:15

Introduction to the VAE Preview 08:15

Variational AutoEncoders Preview 04:29

Reparameterization Trick Preview 04:55

Step 5 - Implementing the CNN-VAE 9 lectures

Welcome to Step 5 - Implementing the CNN-VAE Preview 00:32

Introduction to Step 5 Preview 08:11

Initializing all the parameters and variables of the CNN-VAE class Preview 13:54

Building the Encoder part of the VAE Preview 19:34

Building the "V" part of the VAE Preview 10:40

Building the Decoder part of the VAE Preview 10:40

Implementing the Training operations Preview 18:34

Full Code Section Preview 01:10

The Keras Implementation Preview 02:43

Step 6 - Recurrent Neural Network 7 lectures

Welcome to Step 6 - Recurrent Neural Network Preview 00:20

Plan of Attack Preview 02:32

What are Recurrent Neural Networks? Preview 16:01

The Vanishing Gradient Problem Preview 14:27

LSTMs Preview 19:47

LSTM Practical Intuition Preview 15:11

LSTM Variations Preview 03:36

Step 7 - Mixture Density Network 4 lectures

Welcome to Step 7 - Mixture Density Network Preview 00:21

Introduction to the MDN-RNN Preview 09:28

Mixture Density Networks Preview 09:33

VAE + MDN-RNN Visualization Preview 05:45

Step 8 - Implementing the MDN-RNN 12 lectures

Welcome to Step 8 - Implementing the MDN-RNN Preview 00:41

Initializing all the parameters and variables of the MDN-RNN class Preview 13:42

Building the RNN - Gathering the parameters Preview 09:54

Building the RNN - Creating an LSTM cell with Dropout Preview 16:15

Building the RNN - Setting up the Input, Target, and Output of the RNN Preview 14:54

Building the RNN - Getting the Deterministic Output of the RNN Preview 11:56

Building the MDN - Getting the Input, Hidden Layer and Output of the MDN Preview 13:22

Building the MDN - Getting the MDN parameters Preview 10:57

Implementing the Training operations (Part 1) Preview 15:31

Implementing the Training operations (Part 2) Preview 13:34

Full Code Section Preview 02:48

The Keras Implementation Preview 02:05

Step 9 - Reinforcement Learning 4 lectures

Welcome to Step 9 - Reinforcement Learning Preview 00:15

What is Reinforcement Learning? Preview 11:26

A Pseudo Implementation of Reinforcement Learning for the Full World Model Preview 20:00

Full Code Section Preview 00:09

Step 10 - Deep NeuroEvolution 7 lectures

Welcome to Step 10 - Deep NeuroEvolution Preview 00:40

Deep NeuroEvolution Preview 11:10

Evolution Strategies Preview 09:27

Genetic Algorithms Preview 12:30

Covariance-Matrix Adaptation Evolution Strategy (CMA-ES) Preview 13:25

Parameter-Exploring Policy Gradients (PEPG) Preview 12:55

OpenAI Evolution Strategy Preview 08:30

The Final Run 5 lectures

The Whole Implementation Preview 19:50

Download the whole AI Masterclass folder here Preview 00:35

Installing the required packages Preview 11:38

The Final Race: Human Intelligence vs. Artificial Intelligence Preview 10:15

THANK YOU bonus video Preview 02:40

Bonus Lectures 1 lectures

***YOUR SPECIAL BONUS*** Preview 00:29