Deep Learning

Neural networks that see and hear. Neurons, backpropagation, CNNs, RNNs, optimisers, learning-rate schedules and transfer learning.

• Neural Networks & Backpropagation — How deep learning actually learns. Learn the artificial neuron, activation functions (sigmoid, tanh, ReLU, GELU), multilayer perceptrons and the universal approximation idea, forward pass, loss functions (MSE, cross-entropy), backpropagation via the chain rule, computational graphs and autograd, weight initialisation, vanishing/exploding gradients, batch normalisation, dropout, and training loops in PyTorch — with a NumPy network learning XOR from scratch.
• Deep Learning: CNNs, RNNs, Optimisers & Training at Scale — Architectures that see, listen and read. Learn convolutional neural networks (convolution, kernels, stride, padding, pooling, feature hierarchies, ResNets), computer vision tasks (classification, detection, segmentation), recurrent networks and LSTMs for sequences, optimisers (SGD with momentum, Adam, AdamW), learning-rate schedules (warm-up, cosine), batch size and mixed precision, transfer learning and fine-tuning, data augmentation, and GPU training — with NumPy code for a hand-computed convolution and Adam update.