Lecture Slides

McCulloch-Pitts neuron · Boolean logic gates · Historical timeline · Perceptron model · Learning algorithm · Convergence theorem · Boolean functions & geometry

XOR impossibility proof · Convex hull geometry · Minsky-Papert framework · AI Winter · Cover's theorem · VC dimension · Multi-layer solution

Hebb's postulate · Classical conditioning · Instability problem · Oja's rule · Online PCA · BCM rule · Credit assignment problem

Gradient descent · Loss functions · BP derivation · Four fundamental equations · Activation functions · Vanishing gradient · Universal approximation

Grand timeline 1943–1989 · Three recurring themes · Model comparison · AI Winter lessons · Theory-practice gap · What comes next

CNN motivation · Convolution operation · Architecture from scratch · Training & filter evolution · Capacity experiments · Neuroscience connections

Cross-entropy & KL divergence · Shannon's entropy · Adam optimizer · Automatic differentiation · Micrograd engine · Computational graphs

Tensors & autograd · nn.Module · Training loops · DataLoaders · MNIST MLP & CNN

RNN motivation · BPTT · Vanishing gradients · LSTM gates · Char-RNN · Seq2Seq

Bahdanau attention · Scaled dot-product · Self-attention · Schmidhuber 1991 · Vaswani 2017 Transformer

All slide files, notebooks, and course materials bundled in a single download.