Search Results for author: Ole-Christoffer Granmo

Found 55 papers, 30 papers with code

ConvTextTM: An Explainable Convolutional Tsetlin Machine Framework for Text Classification

no code implementations LREC 2022 Bimal Bhattarai, Ole-Christoffer Granmo, Lei Jiao

Recent advancements in natural language processing (NLP) have reshaped the industry, with powerful language models such as GPT-3 achieving superhuman performance on various tasks.

Decision Making Document Classification +2

Efficient Data Fusion using the Tsetlin Machine

no code implementations26 Oct 2023 Rupsa Saha, Vladimir I. Zadorozhny, Ole-Christoffer Granmo

We propose a novel way of assessing and fusing noisy dynamic data using a Tsetlin Machine.

Harnessing Attention Mechanisms: Efficient Sequence Reduction using Attention-based Autoencoders

no code implementations23 Oct 2023 Daniel Biermann, Fabrizio Palumbo, Morten Goodwin, Ole-Christoffer Granmo

As far as we are aware, no model uses the sequence length reduction step as an additional opportunity to tune the models performance.

Contracting Tsetlin Machine with Absorbing Automata

no code implementations17 Oct 2023 Bimal Bhattarai, Ole-Christoffer Granmo, Lei Jiao, Per-Arne Andersen, Svein Anders Tunheim, Rishad Shafik, Alex Yakovlev

In brief, the TA of each clause literal has both an absorbing Exclude- and an absorbing Include state, making the learning scheme absorbing instead of ergodic.

Generalized Convergence Analysis of Tsetlin Machines: A Probabilistic Approach to Concept Learning

no code implementations3 Oct 2023 Mohamed-Bachir Belaid, Jivitesh Sharma, Lei Jiao, Ole-Christoffer Granmo, Per-Arne Andersen, Anis Yazidi

Tsetlin Machines (TMs) have garnered increasing interest for their ability to learn concepts via propositional formulas and their proven efficiency across various application domains.

Interpretable Machine Learning

Learning Minimalistic Tsetlin Machine Clauses with Markov Boundary-Guided Pruning

1 code implementation12 Sep 2023 Ole-Christoffer Granmo, Per-Arne Andersen, Lei Jiao, Xuan Zhang, Christian Blakely, Tor Tveit

A set of variables is the Markov blanket of a random variable if it contains all the information needed for predicting the variable.

Bayesian Inference

TMComposites: Plug-and-Play Collaboration Between Specialized Tsetlin Machines

1 code implementation9 Sep 2023 Ole-Christoffer Granmo

Tsetlin Machines (TMs) provide a fundamental shift from arithmetic-based to logic-based machine learning.

Image Classification

An FPGA Architecture for Online Learning using the Tsetlin Machine

no code implementations1 Jun 2023 Samuel Prescott, Adrian Wheeldon, Rishad Shafik, Tousif Rahman, Alex Yakovlev, Ole-Christoffer Granmo

We present use cases for online learning using the proposed infrastructure and demonstrate the energy/performance/accuracy trade-offs.

Energy-frugal and Interpretable AI Hardware Design using Learning Automata

no code implementations19 May 2023 Rishad Shafik, Tousif Rahman, Adrian Wheeldon, Ole-Christoffer Granmo, Alex Yakovlev

Our analyses provides the first insights into conflicting design tradeoffs involved in energy-efficient and interpretable decision models for this new artificial intelligence hardware architecture.

Verifying Properties of Tsetlin Machines

1 code implementation25 Mar 2023 Emilia Przybysz, Bimal Bhattarai, Cosimo Persia, Ana Ozaki, Ole-Christoffer Granmo, Jivitesh Sharma

Then, we show the correctness of our encoding and provide results for the properties: adversarial robustness, equivalence, and similarity of TsMs.

Adversarial Robustness Interpretable Machine Learning +2

Interpretable Tsetlin Machine-based Premature Ventricular Contraction Identification

no code implementations20 Jan 2023 Jinbao Zhang, Xuan Zhang, Lei Jiao, Ole-Christoffer Granmo, Yongjun Qian, Fan Pan

In this study, we develop a Tsetlin machine (TM) based architecture for premature ventricular contraction (PVC) identification by analysing long-term ECG signals.

On the Equivalence of the Weighted Tsetlin Machine and the Perceptron

no code implementations27 Dec 2022 Jivitesh Sharma, Ole-Christoffer Granmo, Lei Jiao

Tsetlin Machine (TM) has been gaining popularity as an inherently interpretable machine leaning method that is able to achieve promising performance with low computational complexity on a variety of applications.

CostNet: An End-to-End Framework for Goal-Directed Reinforcement Learning

no code implementations3 Oct 2022 Per-Arne Andersen, Morten Goodwin, Ole-Christoffer Granmo

There are two approaches, model-based and model-free reinforcement learning, that show concrete results in several disciplines.

reinforcement-learning Reinforcement Learning (RL)

Interpretable Option Discovery using Deep Q-Learning and Variational Autoencoders

no code implementations3 Oct 2022 Per-Arne Andersen, Ole-Christoffer Granmo, Morten Goodwin

We show that the DVQN algorithm is a promising approach for identifying initiation and termination conditions for option-based reinforcement learning.

Q-Learning reinforcement-learning +1

CaiRL: A High-Performance Reinforcement Learning Environment Toolkit

1 code implementation3 Oct 2022 Per-Arne Andersen, Morten Goodwin, Ole-Christoffer Granmo

CaiRL also presents the first reinforcement learning toolkit with a built-in JVM and Flash support for running legacy flash games for reinforcement learning research.

OpenAI Gym reinforcement-learning +2

Towards Artificial Virtuous Agents: Games, Dilemmas and Machine Learning

no code implementations30 Aug 2022 Ajay Vishwanath, Einar Duenger Bøhn, Ole-Christoffer Granmo, Charl Maree, Christian Omlin

Using modern day AI techniques, such as affinity-based reinforcement learning and explainable AI, we motivate the implementation of virtuous agents that play such role-playing games, and the examination of their decisions through a virtue ethical lens.

Ethics

Socially Fair Mitigation of Misinformation on Social Networks via Constraint Stochastic Optimization

1 code implementation23 Mar 2022 Ahmed Abouzeid, Ole-Christoffer Granmo, Christian Webersik, Morten Goodwin

We further propose a generic misinformation mitigation algorithm that is robust to different social networks' misinformation statistics, allowing a promising impact in real-world scenarios.

Fairness Misinformation +1

Logic-based AI for Interpretable Board Game Winner Prediction with Tsetlin Machine

no code implementations8 Mar 2022 Charul Giri, Ole-Christoffer Granmo, Herke van Hoof, Christian D. Blakely

Hex is a turn-based two-player connection game with a high branching factor, making the game arbitrarily complex with increasing board sizes.

Tsetlin Machine for Solving Contextual Bandit Problems

1 code implementation4 Feb 2022 Raihan Seraj, Jivitesh Sharma, Ole-Christoffer Granmo

This paper introduces an interpretable contextual bandit algorithm using Tsetlin Machines, which solves complex pattern recognition tasks using propositional logic.

Thompson Sampling

On the Convergence of Tsetlin Machines for the AND and the OR Operators

2 code implementations17 Sep 2021 Lei Jiao, Xuan Zhang, Ole-Christoffer Granmo

The analyses on AND and OR operators, together with the previously analysed 1-bit and XOR operations, complete the convergence analyses on basic operators in Boolean algebra.

Coalesced Multi-Output Tsetlin Machines with Clause Sharing

5 code implementations17 Aug 2021 Sondre Glimsdal, Ole-Christoffer Granmo

While TM and CoTM accuracy is similar when using more than $1$K clauses per class, CoTM reaches peak accuracy $3\times$ faster on MNIST with $8$K clauses.

Drop Clause: Enhancing Performance, Interpretability and Robustness of the Tsetlin Machine

6 code implementations30 May 2021 Jivitesh Sharma, Rohan Yadav, Ole-Christoffer Granmo, Lei Jiao

In this article, we introduce a novel variant of the Tsetlin machine (TM) that randomly drops clauses, the key learning elements of a TM.

Image Classification Interpretable Machine Learning

A Relational Tsetlin Machine with Applications to Natural Language Understanding

5 code implementations22 Feb 2021 Rupsa Saha, Ole-Christoffer Granmo, Vladimir I. Zadorozhny, Morten Goodwin

TMs are a pattern recognition approach that uses finite state machines for learning and propositional logic to represent patterns.

Natural Language Understanding Question Answering

On the Convergence of Tsetlin Machines for the XOR Operator

6 code implementations7 Jan 2021 Lei Jiao, Xuan Zhang, Ole-Christoffer Granmo, K. Darshana Abeyrathna

The Tsetlin Machine (TM) is a novel machine learning algorithm with several distinct properties, including transparent inference and learning using hardware-near building blocks.

Measuring the Novelty of Natural Language Text Using the Conjunctive Clauses of a Tsetlin Machine Text Classifier

5 code implementations17 Nov 2020 Bimal Bhattarai, Ole-Christoffer Granmo, Lei Jiao

The mechanism uses the conjunctive clauses of the TM to measure to what degree a text matches the classes covered by the training data.

Novelty Detection Text Classification

Massively Parallel and Asynchronous Tsetlin Machine Architecture Supporting Almost Constant-Time Scaling

2 code implementations10 Sep 2020 K. Darshana Abeyrathna, Bimal Bhattarai, Morten Goodwin, Saeed Gorji, Ole-Christoffer Granmo, Lei Jiao, Rupsa Saha, Rohan K. Yadav

We evaluated the proposed parallelization across diverse learning tasks and it turns out that our decentralized TM learning algorithm copes well with working on outdated data, resulting in no significant loss in learning accuracy.

On the Convergence of Tsetlin Machines for the IDENTITY- and NOT Operators

no code implementations28 Jul 2020 Xuan Zhang, Lei Jiao, Ole-Christoffer Granmo, Morten Goodwin

The analysis of the convergence of the two basic operators lays the foundation for analyzing other logical operators.

Operator learning

A Novel Multi-Step Finite-State Automaton for Arbitrarily Deterministic Tsetlin Machine Learning

no code implementations4 Jul 2020 K. Darshana Abeyrathna, Ole-Christoffer Granmo, Rishad Shafik, Alex Yakovlev, Adrian Wheeldon, Jie Lei, Morten Goodwin

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.

BIG-bench Machine Learning

Extending the Tsetlin Machine With Integer-Weighted Clauses for Increased Interpretability

4 code implementations11 May 2020 K. Darshana Abeyrathna, Ole-Christoffer Granmo, Morten Goodwin

Here, we address the accuracy-interpretability challenge in machine learning by equipping the TM clauses with integer weights.

A Regression Tsetlin Machine with Integer Weighted Clauses for Compact Pattern Representation

4 code implementations4 Feb 2020 K. Darshana Abeyrathna, Ole-Christoffer Granmo, Morten Goodwin

Although the RTM has solved non-linear regression problems with competitive accuracy, the resolution of the output is proportional to the number of clauses employed.

regression Unity

A Tsetlin Machine with Multigranular Clauses

4 code implementations16 Sep 2019 Saeed Rahimi Gorji, Ole-Christoffer Granmo, Adrian Phoulady, Morten Goodwin

The recently introduced Tsetlin Machine (TM) has provided competitive pattern recognition accuracy in several benchmarks, however, requires a 3-dimensional hyperparameter search.

Specificity

Environment Sound Classification using Multiple Feature Channels and Attention based Deep Convolutional Neural Network

no code implementations28 Aug 2019 Jivitesh Sharma, Ole-Christoffer Granmo, Morten Goodwin

In this paper, we propose a model for the Environment Sound Classification Task (ESC) that consists of multiple feature channels given as input to a Deep Convolutional Neural Network (CNN) with Attention mechanism.

Data Augmentation Environment Sound Classification +2

Towards Model-based Reinforcement Learning for Industry-near Environments

1 code implementation27 Jul 2019 Per-Arne Andersen, Morten Goodwin, Ole-Christoffer Granmo

If these environment dynamics are adequately learned, a model-based approach is perhaps the most sample efficient method for learning agents to act in an environment optimally.

Model-based Reinforcement Learning Q-Learning +2

A Neural Turing~Machine for Conditional Transition Graph Modeling

no code implementations15 Jul 2019 Mehdi Ben Lazreg, Morten Goodwin, Ole-Christoffer Granmo

However, learning the graph structure is often complex, particularly when the graph is cyclic, and the transitions from one node to another are conditioned such as graphs used to represent a finite state machine.

BIG-bench Machine Learning Information Retrieval +2

The Convolutional Tsetlin Machine

8 code implementations arXiv 2019 Ole-Christoffer Granmo, Sondre Glimsdal, Lei Jiao, Morten Goodwin, Christian W. Omlin, Geir Thore Berge

Whereas the TM categorizes an image by employing each clause once to the whole image, the CTM uses each clause as a convolution filter.

Image Classification

The Regression Tsetlin Machine: A Tsetlin Machine for Continuous Output Problems

1 code implementation10 May 2019 K. Darshana Abeyrathna, Ole-Christoffer Granmo, Lei Jiao, Morten Goodwin

We achieve this by: (1) using the conjunctive clauses of the TM to capture arbitrarily complex patterns; (2) mapping these patterns to a continuous output through a novel voting and normalization mechanism; and (3) employing a feedback scheme that updates the TM clauses to minimize the regression error.

General Classification regression

A Scheme for Continuous Input to the Tsetlin Machine with Applications to Forecasting Disease Outbreaks

4 code implementations10 May 2019 K. Darshana Abeyrathna, Ole-Christoffer Granmo, Xuan Zhang, Morten Goodwin

In this paper, we apply a new promising tool for pattern classification, namely, the Tsetlin Machine (TM), to the field of disease forecasting.

Disease Prediction

The Dreaming Variational Autoencoder for Reinforcement Learning Environments

1 code implementation2 Oct 2018 Per-Arne Andersen, Morten Goodwin, Ole-Christoffer Granmo

It is likely that the solution to these problems lies in short- and long-term planning, exploration and memory management for reinforcement learning algorithms.

Management reinforcement-learning +1

Using the Tsetlin Machine to Learn Human-Interpretable Rules for High-Accuracy Text Categorization with Medical Applications

1 code implementation12 Sep 2018 Geir Thore Berge, Ole-Christoffer Granmo, Tor Oddbjørn Tveit, Morten Goodwin, Lei Jiao, Bernt Viggo Matheussen

The Tsetlin Machine either performs on par with or outperforms all of the evaluated methods on both the 20 Newsgroups and IMDb datasets, as well as on a non-public clinical dataset.

Natural Language Understanding Text Categorization

Deep RTS: A Game Environment for Deep Reinforcement Learning in Real-Time Strategy Games

1 code implementation15 Aug 2018 Per-Arne Andersen, Morten Goodwin, Ole-Christoffer Granmo

Reinforcement learning (RL) is an area of research that has blossomed tremendously in recent years and has shown remarkable potential for artificial intelligence based opponents in computer games.

Reinforcement Learning (RL) Starcraft +1

The Tsetlin Machine - A Game Theoretic Bandit Driven Approach to Optimal Pattern Recognition with Propositional Logic

15 code implementations4 Apr 2018 Ole-Christoffer Granmo

Our theoretical analysis establishes that the Nash equilibria of the game align with the propositional formulas that provide optimal pattern recognition accuracy.

Image Classification Unity

FlashRL: A Reinforcement Learning Platform for Flash Games

no code implementations26 Jan 2018 Per-Arne Andersen, Morten Goodwin, Ole-Christoffer Granmo

This paper introduces the Flash Reinforcement Learning platform (FlashRL) which attempts to fill this gap by providing an environment for thousands of Flash games on a novel platform for Flash automation.

reinforcement-learning Reinforcement Learning (RL)

Towards a Deep Reinforcement Learning Approach for Tower Line Wars

no code implementations17 Dec 2017 Per-Arne Andersen, Morten Goodwin, Ole-Christoffer Granmo

We propose a game environment in between Atari 2600 and Starcraft II, particularly targeting Deep Reinforcement Learning algorithm research.

Q-Learning reinforcement-learning +3

Thompson Sampling Guided Stochastic Searching on the Line for Deceptive Environments with Applications to Root-Finding Problems

no code implementations5 Aug 2017 Sondre Glimsdal, Ole-Christoffer Granmo

In this paper, we address a particularly intriguing variant of the multi-armed bandit problem, referred to as the {\it Stochastic Point Location (SPL) Problem}.

Stochastic Optimization Thompson Sampling

Bayesian Unification of Gradient and Bandit-based Learning for Accelerated Global Optimisation

no code implementations28 May 2017 Ole-Christoffer Granmo

Due to the pervasiveness of bandit based optimisation, our scheme opens up for improved performance both in meta-optimisation and in applications where gradient related information is readily available.

Navigate

Cannot find the paper you are looking for? You can Submit a new open access paper.