Fall 2025 Cohort

Deep Learning from Scratch

An intensive, collaborative research project to build a custom Neural Network library. Moving beyond "black box" APIs to understand the mathematics of intelligence.

View Syllabus

Course Schedule

Week 01 Active

Tensors & Matrices

Introduction to high-performance computing. Moving from scalar loops to vectorized operations on GPU hardware.

Go to Module
Week 02 Upcoming

The Perceptron

Geometric interpretation of linear classifiers. The XOR problem and the limitations of single neurons.

Week 03 Upcoming

Backpropagation

Deriving the chain rule for computational graphs. Implementing the Multi-Layer Perceptron (MLP).

Tensors, Matrix Math & The GPU

Theme: "Death to the For-Loop"

Learning Objectives

Array Thinking

Shift from scalar variables to Tensor objects.

Broadcasting

Implicit expansion of dimensions `(N,1)` vs `(1,M)`.

Hardware

SIMD architecture and GPU parallelism.

Required Reading & Viewing

Assignment: The Tensor Gym

Instruction: Create a Google Colab notebook. Solve the following without using `for` loops.

  • 1

    The RGB Flip

    Tensor shape (3, 256, 256). Swap Red (0) and Blue (2) channels.

  • 2

    The Checkerboard

    Generate an 8x8 checkerboard of 0s and 1s using slicing/reshaping.

  • 3

    The Mask

    Replace all values < 0.5 in a random tensor with 0.

Collaborative Task

Phase 1: Setup

Initialize the shared repository environment.

  1. Create GitHub Account
  2. Fork wids_lib
  3. Add students/bio.txt
  4. Submit Pull Request
Open Repository
Weekly Contest

The Vector Racer

Classify MNIST digits using Nearest Neighbor.

Constraint: No loops permitted. Must use GPU broadcasting.