Artificial Intelligence III – Deep Learning in 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

Chapter 3: Installing Deep Learning Library

Lecture 1: Installing Java

Lecture 2: Installing Eclipse

Lecture 3: Installing Maven

Lecture 4: Cloning the libraries from Github

Chapter 4: Deep Neural Networks Theory

Lecture 1: Deep neural networks

Lecture 2: Activation functions

Lecture 3: Loss functions

Lecture 4: Gradient descent / stochastic gradient descent

Lecture 5: Hyperparameters

Lecture 6: Mathematical formulation of deep neural networks

Chapter 5: Deep Neural Networks Implementation

Lecture 1: Deep neural network implementation – XOR problem

Lecture 2: Deep neural network implementation – XOR problem II

Lecture 3: Deep neural network implementation – iris dataset

Lecture 4: Deep neural network implementation – iris dataset II

Chapter 6: Convolutional Neural Networks (CNNs) Theory

Lecture 1: Convolutional neural networks basics

Lecture 2: Feature selection

Lecture 3: Convolutional neural networks – kernel

Lecture 4: Convolutional neural networks – kernel II

Lecture 5: Convolutional neural networks – pooling

Lecture 6: Convolutional neural networks – flattening

Lecture 7: Convolutional neural networks – illustration

Lecture 8: Mathematical formulation of convolution neural networks

Chapter 7: Convolutional Neural Networks (CNNs) Implementation – Digit Classification

Lecture 1: CNN implementation I – digit classification

Lecture 2: CNN implementation II – digit classification

Lecture 3: CNN implementation III – digit classification

Chapter 8: Convolutional Neural Networks (CNNs) Implementation – Smile Detect

Lecture 1: Emoji classification I – handling custom datasets

Lecture 2: Emoji classification II – the dataset

Lecture 3: Emoji classification III – convolutional network

Lecture 4: Emoji classification IV – test

Chapter 9: Recurrent Neural Networks (RNNs) Theory

Lecture 1: Why do recurrent neural networks are important?

Lecture 2: Recurrent neural networks basics

Lecture 3: Vanishing and exploding gradients problem

Lecture 4: Long-short term memory (LSTM) model

Lecture 5: Gated recurrent units (GRUs)

Lecture 6: Mathematical formulation of recurrent neural networks

Chapter 10: Recurrent Neural Networks (RNNs) Implementation

Lecture 1: Google's approach: word2vec method

Lecture 2: Skip-Gram model fundamentals

Lecture 3: Text classification implementation – similar words

Lecture 4: Sentiment analysis implementation I

Lecture 5: Sentiment analysis implementation II

Lecture 6: Sentiment analysis implementation III

Lecture 7: Sentiment analysis implementation IV

Chapter 11: Course Materials (DOWNLOADS)

Lecture 1: Course materials