Artificial Intelligence II – Hands-On Neural Networks (Java)

Course Curriculum

Chapter 1: Introduction

Lecture 1: Introduction

Chapter 2: Artificial Intelligence Basics

Lecture 1: Why to learn artificial intelligence and machine learning?

Lecture 2: Types of artificial intelligence learning methods

Chapter 3: Hopfield Neural Network Theory

Lecture 1: Hopfield neural network introduction

Lecture 2: Hopfield network – weights

Lecture 3: Hopfield neural network – Hebbian learning

Lecture 4: Hopfield neural network – energy

Lecture 5: Measuring the energy of the network

Lecture 6: Hopfield neural network example

Chapter 4: Hopfield Neural Network Implementation

Lecture 1: Hopfield network implementation – utils

Lecture 2: Hopfield network implementation – matrix operations

Lecture 3: Hopfield network implementation – network

Lecture 4: Hopfield network implementation – running the algorithm

Chapter 5: Neural Networks With Backpropagation Theory

Lecture 1: Artificial neural networks – inspiration

Lecture 2: Artificial neural networks – layers

Lecture 3: Artificial neural networks – the model

Lecture 4: Why to use activation functions?

Lecture 5: Neural networks – the big picture

Lecture 6: Using bias nodes in the neural network

Lecture 7: How to measure the error of the network?

Lecture 8: Optimization with gradient descent

Lecture 9: Gradient descent with backpropagation

Lecture 10: Backpropagation explained

Lecture 11: Applications of neural networks I – character recognition

Lecture 12: Applications of neural networks II – stock market forecast

Lecture 13: Deep learning

Lecture 14: Types of neural networks

Chapter 6: Single Perceptron Model

Lecture 1: Perceptron model training

Lecture 2: Perceptron model implementation I

Lecture 3: Perceptron model implementation II

Lecture 4: Perceptron model implementation III

Lecture 5: Trying to solve XOR problem

Lecture 6: Conclusion: linearity and hidden layers

Chapter 7: Backpropagation Implementation

Lecture 1: Structure of the feedforward network

Lecture 2: Backpropagation implementation I – activation function

Lecture 3: Backpropagation implementation II – NeuralNetwork

Lecture 4: Backpropagation implementation III – Layer

Lecture 5: Backpropagation implementation IV – run

Lecture 6: Backpropagation implementation V – train

Chapter 8: Logical Operators

Lecture 1: Logical operators introduction

Lecture 2: Running the neural network: AND

Lecture 3: Running the neural network: OR

Lecture 4: Running the neural network: XOR

Chapter 9: Clustering

Lecture 1: Clustering with neural networks I

Lecture 2: Clustering with neural networks II

Chapter 10: Classification – Iris Dataset

Lecture 1: About the Iris dataset

Lecture 2: Constructing the neural network

Lecture 3: Testing the neural network

Lecture 4: Calculating the accuracy of the model

Chapter 11: Optical Character Recognition (OCR)

Lecture 1: Optical character recognition theory

Lecture 2: Installing paint.net

Lecture 3: Transform an image into numerical data

Lecture 4: Creating the datasets

Lecture 5: OCR with neural network

Chapter 12: Course Materials (DOWNLOADS)

Lecture 1: Course materials