boltzmann-machine

NeuPy is a Tensorflow based python library for prototyping and building neural networks

Computer code collated for use with Artificial Intelligence Engines book by JV Stone

Restricted Boltzmann Machine for collaborative filtering of movies.

Minimum Probability Flow-Boltzmann Machine Learning (MPF-BML) standalone GUI-based application for the inference of maximum entropy distribution parameters

DBM

Simple implementation of the standard Boltzmann Machine model with MATLAB

Implementation of Restricted Machine from scratch using PyTorch

Learn about Recommender Systems: One that predicts binary ratings "Like" or "Not Like", # Boltzmann Machine.

Understanding the working of boltzmann machine.

w/ hebbian learning

Using Monte-Carlo simulated datasets, a completely transparent Boltzmann Machine trained on 1-D Ising chain data is implemented to predict model couplers in the absence of past coupler values. Methods from machine learning applied to theoretical physics are on display in this work.

The unifying open-source library for Quantum Boltzmann Machines: one Gibbs-state core, six backends (dense, statevector, JAX, tensor-network, quantum-circuit, Pauli propagation), arbitrary QFI metrics, and 13 guided tutorials.

This repository contains boltzmann machine, self organizing maps and autoencoder

Restricted Boltzmann Machine Creation as Recommendation System for Movie Review

Energy-based (Ising/Boltzmann) learning substrate for parity-3 — can a local, physics-native contrastive rule both compute and learn the couplings? Part of the Physical Learning Substrates portfolio.

Boltzmann Machine and Self Organizing Maps are implemented in this repository

NeuroBM is a research and educational platform for cognitive modeling using Boltzmann machines. It provides a framework for exploring cognitive dynamics, hypothesis generation, and understanding human-technology interaction patterns. It is only to be used to study how the Human Brain works as technology is all around us in 2025 and onwards.

A Rust implementation of stochastic hashing (stochash), a probabilistic primitive whose input is a buffer of bytes (each interpreted as a probability byte/256) and whose output is a bit-string of the same length, with each bit sampled independently with P(bit_i = 1) = byte_i / 256.