22 citations · 104 across the 25 of their papers we have counts for
25 papers
LakeBench: Benchmarks for Data Discovery over Data Lakes
Kavitha Srinivas, Julian Dolby, Ibrahim Abdelaziz +6
Within enterprises, there is a growing need to intelligently navigate data lakes, specifically focusing on data discovery. Of particular importance to enterprises is the ability to…
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…
MISMATCH: Fine-grained Evaluation of Machine-generated Text with Mismatch Error Types
Keerthiram Murugesan, Sarathkrishna Swaminathan, Soham Dan +9
With the growing interest in large language models, the need for evaluating the quality of machine text compared to reference (typically human-generated) text has become focal atte…
Scalable Learning of Latent Language Structure With Logical Offline Cycle Consistency
Maxwell Crouse, Ramon Astudillo, Tahira Naseem +4
We introduce Logical Offline Cycle Consistency Optimization (LOCCO), a scalable, semi-supervised method for training a neural semantic parser. Conceptually, LOCCO can be viewed as…
Laziness Is a Virtue When It Comes to Compositionality in Neural Semantic Parsing
Maxwell Crouse, Pavan Kapanipathi, Subhajit Chaudhury +4
Nearly all general-purpose neural semantic parsers generate logical forms in a strictly top-down autoregressive fashion. Though such systems have achieved impressive results across…
Mitigating Gradient Bias in Multi-objective Learning: A Provably Convergent Stochastic Approach
Heshan Fernando, Han Shen, Miao Liu +3
Machine learning problems with multiple objective functions appear either in learning with multiple criteria where learning has to make a trade-off between multiple performance met…
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…
Eye of the Beholder: Improved Relation Generalization for Text-based Reinforcement Learning Agents
Keerthiram Murugesan, Subhajit Chaudhury, Kartik Talamadupula
Text-based games (TBGs) have become a popular proving ground for the demonstration of learning-based agents that make decisions in quasi real-world settings. The crux of the proble…
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…
Image inpainting using frequency domain priors
Hiya Roy, Subhajit Chaudhury, Toshihiko Yamasaki +1
In this paper, we present a novel image inpainting technique using frequency domain information. Prior works on image inpainting predict the missing pixels by training neural netwo…
VisualHints: A Visual-Lingual Environment for Multimodal Reinforcement Learning
Thomas Carta, Subhajit Chaudhury, Kartik Talamadupula +1
We present VisualHints, a novel environment for multimodal reinforcement learning (RL) involving text-based interactions along with visual hints (obtained from the environment). Re…
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…
Investigating Generalization in Neural Networks under Optimally Evolved Training Perturbations
Subhajit Chaudhury, Toshihiko Yamasaki
In this paper, we study the generalization properties of neural networks under input perturbations and show that minimal training data corruption by a few pixel modifications can c…
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…
Assessing Robustness of Deep learning Methods in Dermatological Workflow
Sourav Mishra, Subhajit Chaudhury, Hideaki Imaizumi +1
This paper aims to evaluate the suitability of current deep learning methods for clinical workflow especially by focusing on dermatology. Although deep learning methods have been a…
Lunar surface image restoration using U-net based deep neural networks
Hiya Roy, Subhajit Chaudhury, Toshihiko Yamasaki +3
Image restoration is a technique that reconstructs a feasible estimate of the original image from the noisy observation. In this paper, we present a U-Net based deep neural network…
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…
Transfer Learning From Synthetic To Real Images Using Variational Autoencoders For Precise Position Detection
Tadanobu Inoue, Subhajit Chaudhury, Giovanni De Magistris +1
Capturing and labeling camera images in the real world is an expensive task, whereas synthesizing labeled images in a simulation environment is easy for collecting large-scale imag…
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…
Internal Model from Observations for Reward Shaping
Daiki Kimura, Subhajit Chaudhury, Ryuki Tachibana +1
Reinforcement learning methods require careful design involving a reward function to obtain the desired action policy for a given task. In the absence of hand-crafted reward functi…
Transfer learning from synthetic to real images using variational autoencoders for robotic applications
Tadanobu Inoue, Subhajit Chaudhury, Giovanni De Magistris +1
Robotic learning in simulation environments provides a faster, more scalable, and safer training methodology than learning directly with physical robots. Also, synthesizing images…
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…