Step by step livecoding of a deep learning library. Forked from github.com/joelgrus/joelnet.git with some additional comments and a step by step commit workflow
video of the livecoding.
research engineer, Allen Institute for AI
author, Data Science from Scratch
co-host, "Adversarial Learning" podcast
In this talk we'll build a deep learning library from scratch (well, from NumPy) in 45 minutes.
How is that possible? By typing really fast.
Along the way we'll talk about library design, type hinting, Python 3.6, and of course deep learning.
- Tensors
- Loss Functions
- Layers
- Neural Nets
- Optimizers
- Data
- Training
- XOR Example
- FizzBuzz Example