Week 2

$$\gdef \sam #1 {\mathrm{softargmax}(#1)}$$ $$\gdef \vect #1 {\boldsymbol{#1}} $$ $$\gdef \matr #1 {\boldsymbol{#1}} $$ $$\gdef \E {\mathbb{E}} $$ $$\gdef \V {\mathbb{V}} $$ $$\gdef \R {\mathbb{R}} $$ $$\gdef \N {\mathbb{N}} $$ $$\gdef \relu #1 {\texttt{ReLU}(#1)} $$ $$\gdef \D {\,\mathrm{d}} $$ $$\gdef \deriv #1 #2 {\frac{\D #1}{\D #2}}$$ $$\gdef \pd #1 #2 {\frac{\partial #1}{\partial #2}}$$ $$\gdef \set #1 {\left\lbrace #1 \right\rbrace} $$

Lecture part A

We start by understanding what parametrised models are and then discuss what a loss function is. We then look at Gradient-based methods and how it’s used in the backpropagation algorithm in a traditional neural network. We conclude this section by learning how to implement a neural network in PyTorch followed by a discussion on a more generalized form of backpropagation.

Lecture part B

We begin with a concrete example of backpropagation and discuss the dimensions of Jacobian matrices. We then look at various basic neural net modules and compute their gradients, followed by a brief discussion on softmax and logsoftmax. The other topic of discussion in this part is Practical Tricks for backpropagation.

Practicum

We give a brief introduction to supervised learning using artificial neural networks. We expound on the problem formulation and conventions of data used to train these networks. We also discuss how to train a neural network for multi class classification, and how to perform inference once the network is trained.