Introduces feed-forward networks, covering neural network structure, training, activation functions, and optimization, with applications in forecasting and finance.
Covers non-linear dimensionality reduction techniques using autoencoders, deep autoencoders, and convolutional autoencoders for various applications.
Covers modern Neural Network approaches to NLP, focusing on word embeddings, Neural Networks for NLP tasks, and future Transfer Learning techniques.
Introduces deep learning, from logistic regression to neural networks, emphasizing the need for handling non-linearly separable data.
