Neural Computation

Key questions

Key objectives

After this course, I will be able to:

Learning Path

CS 375

“I trained a neural net classifier from scratch.”

  1. Basic array/“tensor” operations in PyTorch
  2. Linear Regression “the hard way” (but black-box optimizer)
  3. Logistic Regression “the hard way”
  4. Multi-layer Perceptron
  5. Gradient Descent
  6. Data Loaders

Materials

Contents

Intro to Array Computing (draft!)
The content may not be revised for this year. If you really want to see it, click the link above.
Linear Regression the Hard Way (draft!)
The content may not be revised for this year. If you really want to see it, click the link above.
From Logistic Regression to the Multi-Layer Perceptron (draft!)
The content may not be revised for this year. If you really want to see it, click the link above.
Softmax (draft!)
The content may not be revised for this year. If you really want to see it, click the link above.
PyTorch and Logistic Regression (draft!)
The content may not be revised for this year. If you really want to see it, click the link above.
Training an MLP by Gradient Descent in PyTorch (draft!)
The content may not be revised for this year. If you really want to see it, click the link above.
Linear Regression the Really Hard Way (gradient descent) (draft!)
The content may not be revised for this year. If you really want to see it, click the link above.
Embeddings (draft!)
The content may not be revised for this year. If you really want to see it, click the link above.
PyTorch Autograd and SGD (draft!)
The content may not be revised for this year. If you really want to see it, click the link above.