Covers the fundamentals of multi-layer neural networks and the training process of fully connected networks with hidden layers.
Introduces Long Short-Term Memory (LSTM) networks as a solution to vanishing and exploding gradients in recurrent neural networks.
Covers Multilayer Perceptrons, artificial neurons, activation functions, matrix notation, flexibility, regularization, regression, and classification tasks.
Introduces deep learning, from logistic regression to neural networks, emphasizing the need for handling non-linearly separable data.
Delves into the impact of deep learning on non-conceptual knowledge systems and the advancements in transformers and generative adversarial networks.
Explores neural networks optimization, including backpropagation, batch normalization, weight initialization, and hyperparameter search strategies.
