{"id":22707160,"url":"https://github.com/cair/deterministic-tsetlin-machine","last_synced_at":"2025-03-29T20:44:51.963Z","repository":{"id":82388270,"uuid":"296324808","full_name":"cair/Deterministic-Tsetlin-Machine","owner":"cair","description":"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.","archived":false,"fork":false,"pushed_at":"2020-09-17T12:50:44.000Z","size":7,"stargazers_count":1,"open_issues_count":0,"forks_count":0,"subscribers_count":6,"default_branch":"master","last_synced_at":"2025-02-04T21:45:13.489Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":null,"language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/cair.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":null,"code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null}},"created_at":"2020-09-17T12:50:06.000Z","updated_at":"2020-11-13T09:29:54.000Z","dependencies_parsed_at":"2023-06-15T11:15:45.711Z","dependency_job_id":null,"html_url":"https://github.com/cair/Deterministic-Tsetlin-Machine","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/cair%2FDeterministic-Tsetlin-Machine","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/cair%2FDeterministic-Tsetlin-Machine/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/cair%2FDeterministic-Tsetlin-Machine/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/cair%2FDeterministic-Tsetlin-Machine/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/cair","download_url":"https://codeload.github.com/cair/Deterministic-Tsetlin-Machine/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":246243553,"owners_count":20746308,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":[],"created_at":"2024-12-10T10:11:39.406Z","updated_at":"2025-03-29T20:44:51.943Z","avatar_url":"https://github.com/cair.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Deterministic-Tsetlin-Machine\nDue 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.\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fcair%2Fdeterministic-tsetlin-machine","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fcair%2Fdeterministic-tsetlin-machine","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fcair%2Fdeterministic-tsetlin-machine/lists"}