Search Results for author: Anis Yazidi

Found 20 papers, 6 papers with code

A Manifold Representation of the Key in Vision Transformers

no code implementations1 Feb 2024 Li Meng, Morten Goodwin, Anis Yazidi, Paal Engelstad

The query, key, and value are often intertwined and generated within those blocks via a single, shared linear transformation.

Instance Segmentation object-detection +2

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

State Representation Learning Using an Unbalanced Atlas

no code implementations17 May 2023 Li Meng, Morten Goodwin, Anis Yazidi, Paal Engelstad

The manifold hypothesis posits that high-dimensional data often lies on a lower-dimensional manifold and that utilizing this manifold as the target space yields more efficient representations.

Dimensionality Reduction Representation Learning +1

Unsupervised Representation Learning in Partially Observable Atari Games

1 code implementation13 Mar 2023 Li Meng, Morten Goodwin, Anis Yazidi, Paal Engelstad

Contrastive methods have performed better than generative models in previous state representation learning research.

Atari Games Representation Learning

Combining datasets to increase the number of samples and improve model fitting

1 code implementation11 Oct 2022 Thu Nguyen, Rabindra Khadka, Nhan Phan, Anis Yazidi, Pål Halvorsen, Michael A. Riegler

For many use cases, combining information from different datasets can be of interest to improve a machine learning model's performance, especially when the number of samples from at least one of the datasets is small.

Imputation Time Series Analysis +1

Towards the Neuroevolution of Low-level Artificial General Intelligence

1 code implementation27 Jul 2022 Sidney Pontes-Filho, Kristoffer Olsen, Anis Yazidi, Michael A. Riegler, Pål Halvorsen, Stefano Nichele

We evaluate a method to evolve a biologically-inspired artificial neural network that learns from environment reactions named Neuroevolution of Artificial General Intelligence (NAGI), a framework for low-level AGI.

Deep Reinforcement Learning with Swin Transformers

1 code implementation30 Jun 2022 Li Meng, Morten Goodwin, Anis Yazidi, Paal Engelstad

Transformers are neural network models that utilize multiple layers of self-attention heads and have exhibited enormous potential in natural language processing tasks.

Atari Games reinforcement-learning +1

Adaptive Learning with Artificial Barriers Yielding Nash Equilibria in General Games

no code implementations28 Mar 2022 Ismail Hassan, B. John Oommen, Anis Yazidi

In this paper, we devise a LA with artificial barriers for solving a general form of stochastic bimatrix game.

improving the Diversity of Bootstrapped DQN by Replacing Priors With Noise

no code implementations2 Mar 2022 Li Meng, Morten Goodwin, Anis Yazidi, Paal Engelstad

In this article, we further explore the possibility of replacing priors with noise and sample the noise from a Gaussian distribution to introduce more diversity into this algorithm.

Atari Games Q-Learning

Artificial Intelligence in Dry Eye Disease

no code implementations2 Sep 2021 Andrea M. Storås, Inga Strümke, Michael A. Riegler, Jakob Grauslund, Hugo L. Hammer, Anis Yazidi, Pål Halvorsen, Kjell G. Gundersen, Tor P. Utheim, Catherine Jackson

Although the term `AI' is commonly used, recent success in its applications to medicine is mainly due to advancements in the sub-field of machine learning, which has been used to automatically classify images and predict medical outcomes.

Expert Q-learning: Deep Reinforcement Learning with Coarse State Values from Offline Expert Examples

no code implementations28 Jun 2021 Li Meng, Anis Yazidi, Morten Goodwin, Paal Engelstad

Using the board game Othello, we compare our algorithm with the baseline Q-learning algorithm, which is a combination of Double Q-learning and Dueling Q-learning.

Imitation Learning Q-Learning +2

DoS and DDoS Mitigation Using Variational Autoencoders

no code implementations14 May 2021 Eirik Molde Bårli, Anis Yazidi, Enrique Herrera Viedma, Hårek Haugerud

Two methods based on the ability of Variational Autoencoders to learn latent representations from network traffic flows are proposed.

Anomaly Detection

Efficient Quantile Tracking Using an Oracle

no code implementations27 Apr 2020 Hugo L. Hammer, Anis Yazidi, Michael A. Riegler, Håvard Rue

The MSE is decomposed in tracking variance and bias and novel and efficient procedures to estimate these quantities are presented.

A hemodynamic decomposition model for detecting cognitive load using functional near-infrared spectroscopy

no code implementations22 Jan 2020 Marco A. Pinto-Orellana, Diego C. Nascimento, Peyman Mirtaheri, Rune Jonassen, Anis Yazidi, Hugo L. Hammer

In the current paper, we introduce a parametric data-driven model for functional near-infrared spectroscopy that decomposes a signal into a series of independent, rescaled, time-shifted, hemodynamic basis functions.

A general representation of dynamical systems for reservoir computing

1 code implementation3 Jul 2019 Sidney Pontes-Filho, Anis Yazidi, Jianhua Zhang, Hugo Hammer, Gustavo B. M. Mello, Ioanna Sandvig, Gunnar Tufte, Stefano Nichele

The advantages of such implementation are its usage on specialized and optimized deep learning libraries, the capabilities to generalize it to other types of networks and the possibility to evolve cellular automata and other dynamical systems in terms of connectivity, update and learning rules.

Achieving Connectivity Between Wide Areas Through Self-Organising Robot Swarm Using Embodied Evolution

no code implementations12 Jul 2018 Erik Aaron Hansen, Stefano Nichele, Anis Yazidi, Hårek Haugerud, Asieh Abolpour Mofrad, Alex Alcocer

Abruptions to the communication infrastructure happens occasionally, where manual dedicated personnel will go out to fix the interruptions, restoring communication abilities.

Artificial Life

Adaptive Task Assignment in Online Learning Environments

no code implementations23 Jun 2016 Per-Arne Andersen, Christian Kråkevik, Morten Goodwin, Anis Yazidi

As main contribution of this paper, we propose a a novel Skill-Based Task Selector (SBTS) algorithm which is able to approximate a student's skill level based on his performance and consequently suggest adequate assignments.

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