activity
20202022
most cited"Is depression related to cannabis?": A knowledge-infused model for Entity and Relation Extraction with Limited Supervision

9 citations · 26 across the 11 of their papers we have counts for

collaborators

14 papers

cs.LG20221 cited

Norm-Scaling for Out-of-Distribution Detection

Deepak Ravikumar, Kaushik Roy

Out-of-Distribution (OoD) inputs are examples that do not belong to the true underlying distribution of the dataset. Research has shown that deep neural nets make confident mispred…

cs.AI20225 cited

Process Knowledge-infused Learning for Suicidality Assessment on Social Media

Kaushik Roy, Manas Gaur, Qi Zhang +1

Improving the performance and natural language explanations of deep learning algorithms is a priority for adoption by humans in the real world. In several domains, such as healthca…

cs.CL2021

BERMo: What can BERT learn from ELMo?

Sangamesh Kodge, Kaushik Roy

We propose BERMo, an architectural modification to BERT, which makes predictions based on a hierarchy of surface, syntactic and semantic language features. We use linear combinatio…

cs.LG2021

RAPID-RL: A Reconfigurable Architecture with Preemptive-Exits for Efficient Deep-Reinforcement Learning

Adarsh Kumar Kosta, Malik Aqeel Anwar, Priyadarshini Panda +2

Present-day Deep Reinforcement Learning (RL) systems show great promise towards building intelligent agents surpassing human-level performance. However, the computational complexit…

cs.LG20211 cited

Complexity-aware Adaptive Training and Inference for Edge-Cloud Distributed AI Systems

Yinghan Long, Indranil Chakraborty, Gopalakrishnan Srinivasan +1

The ubiquitous use of IoT and machine learning applications is creating large amounts of data that require accurate and real-time processing. Although edge-based smart data process…

cs.AI2021

Knowledge-intensive Language Understanding for Explainable AI

Amit Sheth, Manas Gaur, Kaushik Roy +1

AI systems have seen significant adoption in various domains. At the same time, further adoption in some domains is hindered by inability to fully trust an AI system that it will n…