Deep Learning

Deep learning (also known as deep structured learning) is part of a broader family of machine learning methods based on artificial neural networks with representation learning.

PyTorch is an open source machine learning framework that accelerates the path from research prototyping to production deployment.

Get your hands dirty on PyTorch quickly.

A specialized data structure that are very similar to arrays and matrices. In PyTorch, tensors are used to encode the inputs and outputs of a model, as well as the model’s parameters.

Structure A perceptron is a single-layer neural network used for supervised learning of binary classifiers Perceptron $$ g(x) = \underbrace{\sum_{i=0}^n w_i x_i}_{\text{linear separator}} + \underbrace{w_0}_{\text{offset/bias}} $$

A PyTorch a built-in differentiation engine that supports automatic computation of gradient for any computational graph.

Activation functions should be non-linear differentiable (since training with Backpropagation) Q: Why can’t the mapping between layers be linear? A: Compositions of linear functions is still linear, whole network collapses to regression.

A simple yet typical workflow of building and traing a neural network using PyTorch

Quantifies what it means to have a “good” model Different types of loss functions for different tasks, such as: Classification Regression Metric Learning Reinforcement Learning Classification Classification: Predicting a discrete class label