29 citations · 86 across the 23 of their papers we have counts for
23 papers
Using Large Language Models to Automate Category and Trend Analysis of Scientific Articles: An Application in Ophthalmology
Hina Raja, Asim Munawar, Mohammad Delsoz +11
Purpose: In this paper, we present an automated method for article classification, leveraging the power of Large Language Models (LLM). The primary focus is on the field of ophthal…
Learning Symbolic Rules over Abstract Meaning Representations for Textual Reinforcement Learning
Subhajit Chaudhury, Sarathkrishna Swaminathan, Daiki Kimura +8
Text-based reinforcement learning agents have predominantly been neural network-based models with embeddings-based representation, learning uninterpretable policies that often do n…
LOA: Logical Optimal Actions for Text-based Interaction Games
Daiki Kimura, Subhajit Chaudhury, Masaki Ono +6
We present Logical Optimal Actions (LOA), an action decision architecture of reinforcement learning applications with a neuro-symbolic framework which is a combination of neural ne…
Neuro-Symbolic Reinforcement Learning with First-Order Logic
Daiki Kimura, Masaki Ono, Subhajit Chaudhury +6
Deep reinforcement learning (RL) methods often require many trials before convergence, and no direct interpretability of trained policies is provided. In order to achieve fast conv…
Reinforcement Learning with External Knowledge by using Logical Neural Networks
Daiki Kimura, Subhajit Chaudhury, Akifumi Wachi +4
Conventional deep reinforcement learning methods are sample-inefficient and usually require a large number of training trials before convergence. Since such methods operate on an u…
Learning Multiple Sound Source 2D Localization
Guillaume Le Moing, Phongtharin Vinayavekhin, Tadanobu Inoue +4
In this paper, we propose novel deep learning based algorithms for multiple sound source localization. Specifically, we aim to find the 2D Cartesian coordinates of multiple sound s…
Ensemble of Discriminators for Domain Adaptation in Multiple Sound Source 2D Localization
Guillaume Le Moing, Don Joven Agravante, Tadanobu Inoue +4
This paper introduces an ensemble of discriminators that improves the accuracy of a domain adaptation technique for the localization of multiple sound sources. Recently, deep neura…
Data-Efficient Framework for Real-world Multiple Sound Source 2D Localization
Guillaume Le Moing, Phongtharin Vinayavekhin, Don Joven Agravante +4
Deep neural networks have recently led to promising results for the task of multiple sound source localization. Yet, they require a lot of training data to cover a variety of acous…
Bootstrapped Q-learning with Context Relevant Observation Pruning to Generalize in Text-based Games
Subhajit Chaudhury, Daiki Kimura, Kartik Talamadupula +3
We show that Reinforcement Learning (RL) methods for solving Text-Based Games (TBGs) often fail to generalize on unseen games, especially in small data regimes. To address this iss…
Unsupervised Temporal Feature Aggregation for Event Detection in Unstructured Sports Videos
Subhajit Chaudhury, Daiki Kimura, Phongtharin Vinayavekhin +7
Image-based sports analytics enable automatic retrieval of key events in a game to speed up the analytics process for human experts. However, most existing methods focus on structu…
Design and Implementation of Linked Planning Domain Definition Language
Michiaki Tatsubori, Asim Munawar, Takao Moriyama
Planning is a critical component of any artificial intelligence system that concerns the realization of strategies or action sequences typically for intelligent agents and autonomo…
Spatially-weighted Anomaly Detection with Regression Model
Daiki Kimura, Minori Narita, Asim Munawar +1
Visual anomaly detection is common in several applications including medical screening and production quality check. Although a definition of the anomaly is an unknown trend in dat…
Injective State-Image Mapping facilitates Visual Adversarial Imitation Learning
Subhajit Chaudhury, Daiki Kimura, Asim Munawar +1
The growing use of virtual autonomous agents in applications like games and entertainment demands better control policies for natural-looking movements and actions. Unlike the conv…
Constrained Exploration and Recovery from Experience Shaping
Tu-Hoa Pham, Giovanni De Magistris, Don Joven Agravante +3
We consider the problem of reinforcement learning under safety requirements, in which an agent is trained to complete a given task, typically formalized as the maximization of a re…
Safe Exploration in Markov Decision Processes with Time-Variant Safety using Spatio-Temporal Gaussian Process
Akifumi Wachi, Hiroshi Kajino, Asim Munawar
In many real-world applications (e.g., planetary exploration, robot navigation), an autonomous agent must be able to explore a space with guaranteed safety. Most safe exploration a…
Reinforcement Learning Testbed for Power-Consumption Optimization
Takao Moriyama, Giovanni De Magistris, Michiaki Tatsubori +3
Common approaches to control a data-center cooling system rely on approximated system/environment models that are built upon the knowledge of mechanical cooling and electrical and…
Deep Learning with Predictive Control for Human Motion Tracking
Don Joven Agravante, Giovanni De Magistris, Asim Munawar +2
We propose to combine model predictive control with deep learning for the task of accurate human motion tracking with a robot. We design the MPC to allow switching between the lear…
Experimental Force-Torque Dataset for Robot Learning of Multi-Shape Insertion
Giovanni De Magistris, Asim Munawar, Tu-Hoa Pham +3
The accurate modeling of real-world systems and physical interactions is a common challenge towards the resolution of robotics tasks. Machine learning approaches have demonstrated…
Focusing on What is Relevant: Time-Series Learning and Understanding using Attention
Phongtharin Vinayavekhin, Subhajit Chaudhury, Asim Munawar +4
This paper is a contribution towards interpretability of the deep learning models in different applications of time-series. We propose a temporal attention layer that is capable of…
MaestROB: A Robotics Framework for Integrated Orchestration of Low-Level Control and High-Level Reasoning
Asim Munawar, Giovanni De Magistris, Tu-Hoa Pham +5
This paper describes a framework called MaestROB. It is designed to make the robots perform complex tasks with high precision by simple high-level instructions given by natural lan…
Deep Reinforcement Learning for High Precision Assembly Tasks
Tadanobu Inoue, Giovanni De Magistris, Asim Munawar +2
High precision assembly of mechanical parts requires accuracy exceeding the robot precision. Conventional part mating methods used in the current manufacturing requires tedious tun…
Limiting the Reconstruction Capability of Generative Neural Network using Negative Learning
Asim Munawar, Phongtharin Vinayavekhin, Giovanni De Magistris
Generative models are widely used for unsupervised learning with various applications, including data compression and signal restoration. Training methods for such systems focus on…
Conditional generation of multi-modal data using constrained embedding space mapping
Subhajit Chaudhury, Sakyasingha Dasgupta, Asim Munawar +2
We present a conditional generative model that maps low-dimensional embeddings of multiple modalities of data to a common latent space hence extracting semantic relationships betwe…