https://github.com/joelgrus/joelnet

live coding deep learning library
https://github.com/joelgrus/joelnet

Last synced: 4 days ago
JSON representation

live coding deep learning library

• Host: GitHub
• URL: https://github.com/joelgrus/joelnet
• Owner: joelgrus
• License: mit
• Created: 2017-11-21T23:59:06.000Z (about 7 years ago)
• Default Branch: master
• Last Pushed: 2020-05-15T13:27:21.000Z (over 4 years ago)
• Last Synced: 2025-01-01T06:09:50.565Z (11 days ago)
• Language: Python
• Size: 15.6 KB
• Stars: 325
• Watchers: 13
• Forks: 61
• Open Issues: 0
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

README

        
# Livecoding Madness: Let's Build a Deep Learning Library

[video](https://www.youtube.com/watch?v=o64FV-ez6Gw) of the livecoding.

[slides](https://docs.google.com/presentation/d/1y9aC4hbNbcpjw9r6BMSayBmEdmdUwR5us_26X3S2j2M/edit?usp=sharing)

--------

[Joel Grus](http://joelgrus.com)

[@joelgrus](https://twitter.com/joelgrus)

research engineer, [Allen Institute for AI](http://allenai.org)

author, [Data Science from Scratch](http://shop.oreilly.com/product/0636920033400.do)

co-host, ["Adversarial Learning" podcast](http://adversariallearning.com)

# Livecoding Madness: Let's Build a Deep Learning Library

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.

# Here's the plan:

1. Tensors

2. Loss Functions

3. Layers

4. Neural Nets

5. Optimizers

6. Data

7. Training

8. XOR Example

9. FizzBuzz Example