Search Results for author:
Found 41 papers, 20 papers with code
Contrastive Transformer: Contrastive Learning Scheme with Transformer innate Patches
Contrastive Transformer enables existing contrastive learning techniques, often used for image classification, to benefit dense downstream prediction tasks such as semantic segmentation.
Unsupervised Representation Learning in Partially Observable Atari Games
Contrastive methods have performed better than generative models in previous state representation learning research.
A contrastive learning approach for individual re-identification in a wild fish population
In both terrestrial and marine ecology, physical tagging is a frequently used method to study population dynamics and behavior.
A Comparison Between Tsetlin Machines and Deep Neural Networks in the Context of Recommendation Systems
These comparisons are based on model performance, interpretability/explainability, and scalability.
Interpretable Option Discovery using Deep Q-Learning and Variational Autoencoders
We show that the DVQN algorithm is a promising approach for identifying initiation and termination conditions for option-based reinforcement learning.
CostNet: An End-to-End Framework for Goal-Directed Reinforcement Learning
There are two approaches, model-based and model-free reinforcement learning, that show concrete results in several disciplines.
CaiRL: A High-Performance Reinforcement Learning Environment Toolkit
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.
Deep Reinforcement Learning with Swin Transformer
In this article, we further explore the possibility of not modifying the reinforcement learning policy, but only replacing the convolutional neural network architecture with the self-attention architecture from Swin Transformer.
Socially Fair Mitigation of Misinformation on Social Networks via Constraint Stochastic Optimization
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.
improving the Diversity of Bootstrapped DQN by Replacing Priors With Noise
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.
MedAI: Transparency in Medical Image Segmentation
MedAI: Transparency in Medical Image Segmentation is a challenge held for the first time at the Nordic AI Meet that focuses on medical image segmentation and transparency in machine learning (ML)-based systems.
Unlocking the potential of deep learning for marine ecology: overview, applications, and outlook
We provide insight into popular deep learning approaches for ecological data analysis in plain language, focusing on the techniques of supervised learning with deep neural networks, and illustrate challenges and opportunities through established and emerging applications of deep learning to marine ecology.
Self-transfer learning via patches: A prostate cancer triage approach based on bi-parametric MRI
Nevertheless, they rely on large amounts of annotated data which is not common in the medical field.
Expert Q-learning: Deep Reinforcement Learning with Coarse State Values from Offline Expert Examples
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.
Enhancing Interpretable Clauses Semantically using Pretrained Word Representation
The approach significantly enhances the performance and interpretability of TM.
Ranked #8 on
Text Classification
on R52
Improving prostate whole gland segmentation in t2-weighted MRI with synthetically generated data
Whole gland (WG) segmentation of the prostate plays a crucial role in detection, staging and treatment planning of prostate cancer (PCa).
A Relational Tsetlin Machine with Applications to Natural Language Understanding
TMs are a pattern recognition approach that uses finite state machines for learning and propositional logic to represent patterns.
Massively Parallel and Asynchronous Tsetlin Machine Architecture Supporting Almost Constant-Time Scaling
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
The analysis of the convergence of the two basic operators lays the foundation for analyzing other logical operators.
A Novel Multi-Step Finite-State Automaton for Arbitrarily Deterministic Tsetlin Machine Learning
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.
Temperate Fish Detection and Classification: a Deep Learning based Approach
In this paper, we propose a two-step deep learning approach for the detection and classification of temperate fishes without pre-filtering.
Extending the Tsetlin Machine With Integer-Weighted Clauses for Increased Interpretability
Here, we address the accuracy-interpretability challenge in machine learning by equipping the TM clauses with integer weights.
Increasing the Inference and Learning Speed of Tsetlin Machines with Clause Indexing
Instead we use a simple look-up table that indexes the clauses on the features that falsify them.
Interpretability in Word Sense Disambiguation using Tsetlin Machine
Word Sense Disambiguation (WSD) is a longstanding unresolved task in Natural Language Processing.
A Regression Tsetlin Machine with Integer Weighted Clauses for Compact Pattern Representation
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.
A Tsetlin Machine with Multigranular Clauses
The recently introduced Tsetlin Machine (TM) has provided competitive pattern recognition accuracy in several benchmarks, however, requires a 3-dimensional hyperparameter search.
Environment Sound Classification using Multiple Feature Channels and Attention based Deep Convolutional Neural Network
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.
Towards Model-based Reinforcement Learning for Industry-near Environments
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.
A Neural Turing~Machine for Conditional Transition Graph Modeling
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.
The Convolutional Tsetlin Machine
Whereas the TM categorizes an image by employing each clause once to the whole image, the CTM uses each clause as a convolution filter.
Ranked #13 on
Image Classification
on Fashion-MNIST
Deep Q-Learning with Q-Matrix Transfer Learning for Novel Fire Evacuation Environment
We also propose a new reinforcement learning approach that entails pretraining the network weights of a DQN based agents to incorporate information on the shortest path to the exit.
The Regression Tsetlin Machine: A Tsetlin Machine for Continuous Output Problems
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.
A Scheme for Continuous Input to the Tsetlin Machine with Applications to Forecasting Disease Outbreaks
In this paper, we apply a new promising tool for pattern classification, namely, the Tsetlin Machine (TM), to the field of disease forecasting.
Biometric Fish Classification of Temperate Species Using Convolutional Neural Network with Squeeze-and-Excitation
The second step is to train the classifier based on a new data set consisting of species that we are interested in for classification, named as post-training.
The Dreaming Variational Autoencoder for Reinforcement Learning Environments
It is likely that the solution to these problems lies in short- and long-term planning, exploration and memory management for reinforcement learning algorithms.
Using the Tsetlin Machine to Learn Human-Interpretable Rules for High-Accuracy Text Categorization with Medical Applications
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.
Deep RTS: A Game Environment for Deep Reinforcement Learning in Real-Time Strategy Games
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.
Combining a Context Aware Neural Network with a Denoising Autoencoder for Measuring String Similarities
This paper proposes a string metric that encompasses similarities between strings based on (1) the character similarities between the words including.
FlashRL: A Reinforcement Learning Platform for Flash Games
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.
Towards a Deep Reinforcement Learning Approach for Tower Line Wars
We propose a game environment in between Atari 2600 and Starcraft II, particularly targeting Deep Reinforcement Learning algorithm research.
Adaptive Task Assignment in Online Learning Environments
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.
