cair/tmu

Stars
106
Rank 325,871 (Top 7 %)
Language
Python
License
MIT License
Created almost 3 years ago
Updated 8 months ago

cair/tmu

cair

There are no reviews yet. Be the first to send feedback to the community and the maintainers!

Implements the Tsetlin Machine, Coalesced Tsetlin Machine, Convolutional Tsetlin Machine, Regression Tsetlin Machine, and Weighted Tsetlin Machine, with support for continuous features, drop clause, Type III Feedback, focused negative sampling, multi-task classifier, autoencoder, literal budget, and one-vs-one multi-class classifier. TMU is written in Python with wrappers for C and CUDA-based clause evaluation and updating.

Tsetlin Machine Unified (TMU) - One Codebase to Rule Them All

TMU is a comprehensive repository that encompasses several Tsetlin Machine implementations. Offering a rich set of features and extensions, it serves as a central resource for enthusiasts and researchers alike.

Features

Core Implementations:
- Tsetlin Machine
- Coalesced Tsetlin Machine
- Convolutional Tsetlin Machine
- Regression Tsetlin Machine
- Weighted Tsetlin Machine
- Autoencoder
- Multi-task Classifier (Upcoming)
- One-vs-one Multi-class Classifier (Upcoming)
- Relational Tsetlin Machine (In Progress)
Extended Features:
- Support for Continuous Features
- Drop Clause
- Literal Budget
- Focused Negative Sampling
- Type III Feedback
- Incremental Clause Evaluation (Upcoming)
- Sparse Computation with Absorbing Actions
- TMComposites: Plug-and-Play Collaboration Between Specialized Tsetlin Machines (In Progress)
Wrappers for C and CUDA-based clause evaluation and updates to enable high-performance computation.

📦 Installation

Prerequisites for Windows

Before installing TMU on Windows, ensure you have the MSVC build tools. Follow these steps:

Download MSVC build tools
Install the Workloads → Desktop development with C++ package. (Note: The package size is about 6-7GB.)

Dependencies

Ubuntu: sudo apt install libffi-dev

Installing TMU

To get started with TMU, run the following command:

pip install git+https://github.com/cair/tmu.git

🛠 Development

If you're looking to contribute or experiment with the codebase, follow these steps:

Clone the Repository:

git clone [email protected]:cair/tmu.git

Set Up Development Environment: Navigate to the project directory and compile the C library:
```
cd tmu && pip install develop .
```
Starting a New Project: For your projects, simply create a new folder within 'examples' and initiate your development.

Modifying the C Codebase

If you make changes to the C codebase, ensure you recompile the code using:

pip install develop .

TsetlinMachine

Code and datasets for the Tsetlin Machine

Fire-Detection-Image-Dataset

This dataset contains normal images and images with fire. It is highly unbalanced to reciprocate real world situations. It consists of a variety of scenarios and different fire situations (intensity, luminosity, size, environment etc).

deep-rts

A Real-Time-Strategy game for Deep Learning research

pyTsetlinMachine

Implements the Tsetlin Machine, Convolutional Tsetlin Machine, Regression Tsetlin Machine, Weighted Tsetlin Machine, and Embedding Tsetlin Machine, with support for continuous features, multigranularity, clause indexing, and literal budget

pyVNC

VNC Client Library for Python

fast-tsetlin-machine-with-mnist-demo

A fast Tsetlin Machine implementation employing bit-wise operators, with MNIST demo.

convolutional-tsetlin-machine-tutorial

Tutorial on the Convolutional Tsetlin Machine

TextUnderstandingTsetlinMachine

Using the Tsetlin Machine to learn human-interpretable rules for high-accuracy text categorization with medical applications

PyTsetlinMachineCUDA

Massively Parallel and Asynchronous Architecture for Logic-based AI

pyTsetlinMachineParallel

Multi-threaded implementation of the Tsetlin Machine, Convolutional Tsetlin Machine, Regression Tsetlin Machine, and Weighted Tsetlin Machine, with support for continuous features and multigranularity.

TsetlinMachineBook

Python code accompanying the book "An Introduction to Tsetlin Machines".

Jupyter Notebook

FlashRL

fast-tsetlin-machine-in-cuda-with-imdb-demo

A CUDA implementation of the Tsetlin Machine based on bitwise operators

deep_maze

open-tsetlin-machine

Open Source Tsetlin Machine framework

TsetlinMachineC

A C implementation of the Tsetlin Machine

rl

awesome-tsetlin-machine

A curated list of Tsetlin Machine research

regression-tsetlin-machine

Implementation of the Regression Tsetlin Machine

deep-warehouse

A Simulator for complex logistic environments

TM-XOR-proof

#tsetlin-machine #machine-learning #game-theory #propositional-logic #pattern-recognition #bandit-learning #frequent-pattern-mining #learning-automata

Axis_and_Allies

A simple Axis & Allies engine.

python-fast-tsetlin-machine

Python wrapper for https://github.com/cair/fast-tsetlin-machine-with-mnist-demo

tmu-datasets

A dataset repository for datasets in tmu

ICML-Massively-Parallel-and-Asynchronous-Tsetlin-Machine-Architecture

Code repository for ICML 21 for Paper titled Massively Parallel and Asynchronous Tsetlin Machine Architecture

ikt111

notebooks

A collection of jupyter notebooks

Jupyter Notebook

Fire-Scene-Parsing

py_image_stitcher

A small library for stitching together images, from Numpy or PIL Sources

deep-line-wars

Docker-Tutorial

A docker tutorial for cair-gpu's

ray-bugfix

A workaround to issues with Rllib, given it does not work for your current gym environment. CarRacing-v0 is one of these.

fire

deep-line-wars-2

Deterministic-Tsetlin-Machine

Due to the high energy consumption and scalability challenges of deep learning, there is a critical need to shift research focus towards dealing with energy consumption constraints. Tsetlin Machines (TMs) are a recent approach to machine learning that has demonstrated significantly reduced energy usage compared to neural networks alike, while performing competitively accuracy-wise on several benchmarks. However, TMs rely heavily on energy-costly random number generation to stochastically guide a team of Tsetlin Automata to a Nash Equilibrium of the TM game. In this paper, we propose a novel finite-state learning automaton that can replace the Tsetlin Automata in TM learning, for increased determinism. The new automaton uses multi-step deterministic state jumps to reinforce sub-patterns. Simultaneously, flipping a coin to skip every d'th state update ensures diversification by randomization. The d-parameter thus allows the degree of randomization to be finely controlled. E.g., d=1 makes every update random and d=infinity makes the automaton completely deterministic. Our empirical results show that, overall, only substantial degrees of determinism reduces accuracy. Energy-wise, random number generation constitutes switching energy consumption of the TM, saving up to 11 mW power for larger datasets with high d values. We can thus use the new d-parameter to trade off accuracy against energy consumption, to facilitate low-energy machine learning.

DeepAxie

Implementation of a simplified Axie Infinity Environment in C++ that is used to train an agent with the reinforcement learning algorithm DQN to play the game.

Tsetlin-Machine-Deep-Neural-Network-Recommendation-System-Comparison

Jupyter Notebook

LogicalTransformerWithTsetlinMachine