Artificial Intelligence Masterclass + ChatGPT Prize [2024]

Course Curriculum

Chapter 1: Introduction

Lecture 1: Welcome Challenge!

Lecture 2: Introduction + Course Structure + Demo

Lecture 3: Learning Paths

Lecture 4: Your Three Best Resources

Lecture 5: Download the Resources here

Lecture 6: Meet your instructors!

Chapter 2: Step 1 – Artificial Neural Network

Lecture 1: Welcome to Step 1 – Artificial Neural Network

Lecture 2: Plan of Attack

Lecture 3: The Neuron

Lecture 4: The Activation Function

Lecture 5: How do Neural Networks work?

Lecture 6: How do Neural Networks learn?

Lecture 7: Gradient Descent

Lecture 8: Stochastic Gradient Descent

Lecture 9: Backpropagation

Chapter 3: Step 2 – Convolutional Neural Network

Lecture 1: Welcome to Step 2 – Convolutional Neural Network

Lecture 2: Plan of Attack

Lecture 3: What are Convolutional Neural Networks?

Lecture 4: Step 1 – The Convolution Operation

Lecture 5: Step 1 Bis – The ReLU Layer

Lecture 6: Step 2 – Pooling

Lecture 7: Step 3 – Flattening

Lecture 8: Step 4 – Full Connection

Lecture 9: Summary

Lecture 10: Softmax & Cross-Entropy

Chapter 4: Step 3 – AutoEncoder

Lecture 1: Welcome to Step 3 – AutoEncoder

Lecture 2: Plan of Attack

Lecture 3: What are AutoEncoders?

Lecture 4: A Note on Biases

Lecture 5: Training an AutoEncoder

Lecture 6: Overcomplete Hidden Layers

Lecture 7: Sparse AutoEncoders

Lecture 8: Denoising AutoEncoders

Lecture 9: Contractive AutoEncoders

Lecture 10: Stacked AutoEncoders

Lecture 11: Deep AutoEncoders

Chapter 5: Step 4 – Variational AutoEncoder

Lecture 1: Welcome to Step 4 – Variational AutoEncoder

Lecture 2: Introduction to the VAE

Lecture 3: Variational AutoEncoders

Lecture 4: Reparameterization Trick

Chapter 6: Step 5 – Implementing the CNN-VAE

Lecture 1: Welcome to Step 5 – Implementing the CNN-VAE

Lecture 2: Introduction to Step 5

Lecture 3: Initializing all the parameters and variables of the CNN-VAE class

Lecture 4: Building the Encoder part of the VAE

Lecture 5: Building the "V" part of the VAE

Lecture 6: Building the Decoder part of the VAE

Lecture 7: Implementing the Training operations

Lecture 8: Full Code Section

Lecture 9: The Keras Implementation

Chapter 7: Step 6 – Recurrent Neural Network

Lecture 1: Welcome to Step 6 – Recurrent Neural Network

Lecture 2: Plan of Attack

Lecture 3: What are Recurrent Neural Networks?

Lecture 4: The Vanishing Gradient Problem

Lecture 5: LSTMs

Lecture 6: LSTM Practical Intuition

Lecture 7: LSTM Variations

Chapter 8: Step 7 – Mixture Density Network

Lecture 1: Welcome to Step 7 – Mixture Density Network

Lecture 2: Introduction to the MDN-RNN

Lecture 3: Mixture Density Networks

Lecture 4: VAE + MDN-RNN Visualization

Chapter 9: Step 8 – Implementing the MDN-RNN

Lecture 1: Welcome to Step 8 – Implementing the MDN-RNN

Lecture 2: Initializing all the parameters and variables of the MDN-RNN class

Lecture 3: Building the RNN – Gathering the parameters

Lecture 4: Building the RNN – Creating an LSTM cell with Dropout

Lecture 5: Building the RNN – Setting up the Input, Target, and Output of the RNN

Lecture 6: Building the RNN – Getting the Deterministic Output of the RNN

Lecture 7: Building the MDN – Getting the Input, Hidden Layer and Output of the MDN

Lecture 8: Building the MDN – Getting the MDN parameters

Lecture 9: Implementing the Training operations (Part 1)

Lecture 10: Implementing the Training operations (Part 2)

Lecture 11: Full Code Section

Lecture 12: The Keras Implementation

Chapter 10: Step 9 – Reinforcement Learning

Lecture 1: Welcome to Step 9 – Reinforcement Learning

Lecture 2: What is Reinforcement Learning?

Lecture 3: A Pseudo Implementation of Reinforcement Learning for the Full World Model

Lecture 4: Full Code Section

Chapter 11: Step 10 – Deep NeuroEvolution

Lecture 1: Welcome to Step 10 – Deep NeuroEvolution

Lecture 2: Deep NeuroEvolution

Lecture 3: Evolution Strategies

Lecture 4: Genetic Algorithms

Lecture 5: Covariance-Matrix Adaptation Evolution Strategy (CMA-ES)

Lecture 6: Parameter-Exploring Policy Gradients (PEPG)

Lecture 7: OpenAI Evolution Strategy

Chapter 12: The Final Run

Lecture 1: The Whole Implementation

Lecture 2: Download the whole AI Masterclass folder here

Lecture 3: Installing the required packages

Lecture 4: The Final Race: Human Intelligence vs. Artificial Intelligence

Lecture 5: THANK YOU Video