Artificial Intelligence Masterclass – Skillcept Online

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

Download the whole AI Masterclass folder containing the entire implementation of the Full World Model trained for the Project. You will find everything in the zip folder (Download by clicking Link Below)

Note : Download Link Only Available for Enrolled Students

Course Content

Expand All

Introduction 2 Lessons

Expand

Section Content

0% Complete 0/2 Steps

Introduction + Course Structure + Demo

Your Three Best Resources

Step 1 – Artificial Neural Network 9 Lessons

Expand

Section Content

0% Complete 0/9 Steps

Welcome to Step 1 – Artificial Neural Network

The Activation Function

How do Neural Networks work?

How do Neural Networks learn?

Gradient Descent

Stochastic Gradient Descent

Backpropagation

Step 2 – Convolutional Neural Network 10 Lessons

Expand

Section Content

0% Complete 0/10 Steps

Welcome to Step 2 – Convolutional Neural Network

What are Convolutional Neural Networks?

Step 1 – The Convolution Operation

Step 1 (B) – The ReLU Layer

Step 2 – Pooling

Step 3 – Flattening

Step 4 – Full Connection

Softmax & Cross-Entropy

Step 3 – AutoEncoder 11 Lessons

Expand

Section Content

0% Complete 0/11 Steps

Welcome to Step 3 – AutoEncoder

What are AutoEncoders?

A Note on Biases

Training an AutoEncoder

Overcomplete Hidden Layers

Sparse AutoEncoders

Denoising AutoEncoders

Contractive AutoEncoders

Stacked AutoEncoders

1 of 2

Step 4 – Variational AutoEncoder 4 Lessons

Expand

Section Content

0% Complete 0/4 Steps

Welcome to Step 4 – Variational AutoEncoder

Introduction to the VAE

Variational AutoEncoders

Reparameterization Trick

Step 5 – Implementing the CNN-VAE 9 Lessons

Expand

Section Content

0% Complete 0/9 Steps

Welcome to Step 5 – Implementing the CNN-VAE

Introduction to Step 5

Initializing all the parameters and variables of the CNN-VAE class

Building the Encoder part of the VAE

Building the “V” part of the VAE

Building the Decoder part of the VAE

Implementing the Training operations

Full Code Section

The Keras Implementation

Step 6 – Recurrent Neural Network 7 Lessons

Expand

Section Content

0% Complete 0/7 Steps

Welcome to Step 6 – Recurrent Neural Network

What are Recurrent Neural Networks?

The Vanishing Gradient Problem

LSTM Practical Intuition

LSTM Variations

Step 7 – Mixture Density Network 4 Lessons

Expand

Section Content

0% Complete 0/4 Steps

Welcome to Step 7 – Mixture Density Network

Introduction to MDN-RNN

Mixture Density Networks

VAE + MDN-RNN Visualization

Step 8 – Implementing the MDN-RNN 12 Lessons

Expand

Section Content

0% Complete 0/12 Steps

Welcome to Step 8 – Implementing the MDN-RNN

Initializing all the parameters and variables of the MDN-RNN class

Building the RNN – Gathering the parameters

Building the RNN – Creating an LSTM cell with Dropout

Building the RNN – Setting up the Input, Target, and Output of the RNN

Building the RNN – Getting the Deterministic Output of the RNN

Building the MDN – Getting the Input, Hidden Layer and Output of the MDN

Building the MDN – Getting the MDN parameters

Implementing the Training operations (Part 1)

Implementing the Training operations (Part 2)

1 of 2

Step 9 – Reinforcement Learning 4 Lessons

Expand

Section Content

0% Complete 0/4 Steps

Welcome to Step 9 – Reinforcement Learning

What is Reinforcement Learning?

A Pseudo Implementation of Reinforcement Learning for the Full World Model

Full Code Section

1 of 2