Robbepop/prophet
A simple neural net implementation.
This is a neural network library written in Rust for developers who need to implement supervised learning models efficiently. It takes in structured numerical data and produces a trained neural network model capable of making predictions. This is for software engineers and machine learning practitioners who are building applications in Rust.
No commits in the last 6 months.
Use this if you are a Rust developer needing a foundational, cache-efficient, and performant neural network implementation for supervised learning with fully connected layers.
Not ideal if you need deep learning features like convolutional layers, GPU acceleration, or support for unsupervised learning or reinforcement learning.
Stars
41
Forks
1
Language
Rust
License
—
Category
Last pushed
Jul 31, 2019
Monthly downloads
99
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/Robbepop/prophet"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
SyntaxSpirits/rust-lstm
A complete LSTM neural network library with training capabilities, multiple optimizers, and...
MikhailKravets/NeuroFlow
Awesome deep learning crate
xaynetwork/xaynet
Xaynet represents an agnostic Federated Machine Learning framework to build privacy-preserving...
DragonflyRobotics/Neuroxide
Ultrafast PyTorch-like AI Framework Written from Ground-Up in Rust
scallop-lang/scallop
Framework and Language for Neurosymbolic Programming.