Please log in to watch this conference skillscast.
During this talk, you will learn how to use Haskell's powerful features for abstraction to create a Neural Network library in native Haskell that makes it easy to create complex network architectures in a type-safe and flexible way. Automatic differentiation is used to provide painless gradient descent and easy extension with new components without the need to first compute complicated partial derivatives by hand. Furthermore, the API uses "Pipes" for separation of concerns (data import, training, reporting, termination).
YOU MAY ALSO LIKE:
- This Ain't Your Daddy's Probability Monad - Modelling Probabilistic Time in Haskell (SkillsCast recorded in October 2019)
- Haskell eXchange 2021 (Online Conference on 16th - 17th November 2021)
- Theorems for Free (SkillsCast recorded in November 2020)
- Comparing Strict and Lazy (SkillsCast recorded in November 2020)
Neural Nets with Automatic Differentiation