 hopfield-networks
 hopfield-networks 
 Hopfield Network simulator
 An implementation of Hopfield Networks in Haskell, a type of neural network used for unsupervised learning and memory simulation.
Hopfield Networks for unsupervised learning in Haskell
16 stars
 4 watching
 2 forks
 
Language: Haskell 
last commit: over 11 years ago 
Linked from   1 awesome list  
 Related projects:
| Repository | Description | Stars | 
|---|---|---|
|  | Implementations of basic machine learning algorithms in Haskell | 57 | 
|  | An implementation of Interaction Networks for learning physical simulations and generalizing to novel systems | 131 | 
|  | A DSL and toolkit for designing and optimizing deep neural networks in Haskell | 702 | 
|  | A library for building complex neural networks in Haskell with a focus on dependently typed specifications and composability | 1,451 | 
|  | A Haskell library for building neural networks | 112 | 
|  | A Haskell library for building neural networks and working with tensors. | 1,083 | 
|  | An iOS playground project demonstrating neural network concepts and computer vision using pure Swift code. | 381 | 
|  | A set of network stack examples in Haskell designed to test and demonstrate various network protocols. | 115 | 
|  | A PyTorch implementation of a neural network potential for molecular simulations | 471 | 
|  | A toy implementation of the Raft protocol with an experimental BFT variant in Haskell. | 111 | 
|  | A Haskell-based framework for flexible neural networks and similar parameterized models with automatic differentiation and modular training algorithms. | 124 | 
|  | Haskell bindings for a popular machine learning framework, allowing developers to build and deploy neural networks in the Haskell programming language. | 1,583 | 
|  | A PyTorch-based neural network training framework with advanced features and utilities | 398 | 
|  | An artificial neural network library for rapid prototyping and extension in Haskell. | 378 | 
|  | A MATLAB implementation of a deep belief network used for generative learning and visualization of the neural network simulation process. | 48 |