Course Notes
Witten by students for extra credit, with editing by instructors. For details on how to submit, see here.
-
Lecture 07: Multi-layer Perceptrons and Backpropagation
From binary to multi-class classification with softmax, stacking fully-connected layers into a multi-layer perceptron, the nonlinear activations that finally solve XOR, and backpropagation in matrix form.
-
Lecture 06: Automatic Differentiation with PyTorch and Project Discussion
From Bernoulli likelihoods to loss functions, PyTorch autograd, model construction, training and evaluation loops, debugging with hooks, and final-project planning.
-
Lecture 05: Parameter Optimization and Gradient Descent
From the perceptron's hard threshold to a smooth sigmoid unit, maximum likelihood, stochastic gradient descent, and backpropagation on computation graphs.
-
Lecture 04: Single-layer networks
From inputs and weights to the perceptron, decision boundaries, the Perceptron Learning Algorithm, and multi-neuron networks.
-
Lecture 03 - Stats / Linear Algebra Review
The fundamental math skills for deep learning - tensors and PyTorch, vectors, matrices and broadcasting, probability basics, estimation (MLE and MAP), and linear regression.
-
Lecture Notes from Lecture 2
Introduction to Deep Learning and Generative Models
-
Lecture Notes from Lecture 1
Course Overview and Intro to Machine Learning
-
Lecture Notes Template
An example of a distill-style lecture notes that showcases the main elements.