leamoon/StochasticNet
Nerual Network of Stochastic Computing for MNIST Recognition
This project explores building neural networks using stochastic computing within Minecraft's Redstone circuits. It takes a 15x15 pixel image of a handwritten digit as input and attempts to recognize the digit, outputting a classification with up to 80% accuracy. This is primarily for digital circuit designers, hobbyists, or researchers interested in unconventional computing methods and hardware neural networks.
225 stars. No commits in the last 6 months.
Use this if you are a digital circuit designer or hobbyist exploring alternative, simplified architectures for neural networks, especially within constrained or non-traditional computing environments like Minecraft's Redstone.
Not ideal if you need a high-performance, real-time, or production-ready handwritten digit recognition system, as its practical recognition time exceeds 20 minutes due to Minecraft's limitations.
Stars
225
Forks
11
Language
Python
License
MIT
Category
Last pushed
Jul 01, 2022
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/leamoon/StochasticNet"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
Jasonnor/Backpropagation
Implementing multilayer neural networks through backpropagation using Java.
dlidstrom/NeuralNetworkInAllLangs
Vanilla neural network implemented in all major languages
goessl/MachineLearning
An easy neural network for Java!
evolvingstuff/RecurrentJava
Deep Recurrent Neural Nets in Java
amanmehara/tantrika
An object oriented neural network library.