Fuzzy-Pattern Tsetlin Machine for Text Generation

A new implementation of the Fuzzy-Pattern Tsetlin Machine achieves 37 million MNIST predictions per second at 98% accuracy with 4.7 GB/s throughput on a desktop CPU, and demonstrates the first Tsetlin Machine–based text generation example. The implementation, developed by BooBSD, offers up to 15× faster training and 41× faster inference compared to the original FPTM implementation through bitwise operations, SIMD instructions, and a specialized memory layout.

Speed is the most important feature. Fred Wilson This repository provides an alternative Fuzzy-Pattern Tsetlin Machine https://github.com/BooBSD/FuzzyPatternTM implementation with zero external dependencies and blazingly fast performance. Achieves 37 million MNIST predictions per second at 98% accuracy with 4.7 GB/s throughput on a desktop CPU and demonstrates the first Tsetlin Machine–based text generation example. - Up to 15× faster training and 41× faster inference compared to the original FPTM implementation, achieved through the use of bitwise operations, SIMD instructions, and a specialized memory layout. - Binary classifier. - Multi-class classifier. - Single-threaded and multi-threaded training and inference. - Specialized BitSet index over literals to improve performance on very large, sparse binary vector inputs. - Model compilation to reduce memory usage and increase inference speed. - Save and load trained models for production deployment or continued training with modified hyperparameters. - Automatic selection of UInt8 or UInt16 Tsetlin Automata based on the number of TA states. - Automatic switching between binary and multi-class classification depending on the dataset. - Built-in benchmarking tool. - Built-in explainability tools. Talk is cheap, show me the~~code~~some examples. Below is an example of character-level text generation in the style of Shakespeare. First, install the Julia language https://julialang.org by running the following command and following the installation instructions: curl -fsSL https://install.julialang.org | sh In the first terminal window , run the following command to train the model over multiple epochs: julia -O3 -t auto examples/TEXT/train.jl In the second terminal window , run the following command after each training epoch to observe how the quality of the generated text evolves from one epoch to the next: julia -O3 examples/TEXT/sample.jl After 400+ epochs, you should see output similar to the following: ROMEO: The father's death, And then I shall be so; For I have done that was a queen, That I may be so, my lord. JULIET: I would have should be so, for the prince, And then I shall be so; For the princely father with the princess, And then I shall be the virtue of your soul, Which your son,-- ESCALUS: What, what should be particular me to death. BUCKINGHAM: God save the queen's proclaim'd: Come, come, the Duke of York. KING EDWARD IV: So do I do not know the prince, And then I shall be so, and such a part. KING RICHARD III: Shall I be some confess the state, Which way the sun the prince's dead; And then I will be so. Here is a quick "Hello, World " example of a typical use case with the Tsetlin Machine. Importing the necessary functions and the MNIST dataset: using MLDatasets: MNIST using .Tsetlin: TMInput, TMClassifier, train , predict, accuracy, save, load, unzip, booleanize, compile, benchmark x train, y train = unzip MNIST :train ... x test, y test = unzip MNIST :test ... Booleanizing input data 2 bits per pixel : x train = booleanize x, 0, 0.5 for x in x train x test = booleanize x, 0, 0.5 for x in x test This implementation introduces some differences compared to the Vanilla Tsetlin Machine : L — limits the number of included literals in a clause. LF — new hyperparameter that sets the number of literal misses allowed per clause. CLAUSES = 20 Number of clauses per class T = 20 Voting threshold S = 200 Specificity L = 150 Maximum literals per clause LF = 75 Allowed failed literals per clause EPOCHS = 1000 Number of training epochs Train the model over 1000 epochs and save the compiled model to disk: tm = TMClassifier x train 1 , y train, CLAUSES, T, S, L, LF, states num=256, include limit=240 train tm, x train, y train, x test, y test, EPOCHS, shuffle=true, index=false save compile tm , "/tmp/tm last.tm" Loading the compiled model and evaluating accuracy: tm = load "/tmp/tm last.tm" accuracy predict tm, x test , y test | println Benchmarking the compiled model: benchmark tm, x test, y test, 1000 4, warmup=true, index=false 37 million MNIST predictions per second on a CPU. To explain a specific input vector or generate a heat map of the distributed literal representation on the MNIST dataset, run the following command: julia -O3 -t auto examples/MNIST/explain.jl This repository includes examples for MNIST , Fashion-MNIST , CIFAR-10 , AmazonSales , IMDb sentiment analysis, Noisy Parity Problem , and Shakespeare character-level text generation . Instructions on how to run the examples can be found here https://github.com/BooBSD/Tsetlin.jl/tree/main/examples . If you use the Fuzzy-Pattern Tsetlin Machine in a scientific publication, please cite the following paper: arXiv:2508.08350 https://arxiv.org/abs/2508.08350 @article{hnilov2025fptm, title={Fuzzy-Pattern Tsetlin Machine}, author={Artem Hnilov}, journal={arXiv preprint arXiv.2508.08350}, year={2025}, eprint={2508.08350}, archivePrefix={arXiv}, primaryClass={cs.LG}, url={https://arxiv.org/abs/2508.08350}, doi = {10.48550/arXiv.2508.08350}, }