Kaushik Roy

Stimulating STDP to Exploit Locality for Lifelong Learning without Catastrophic Forgetting.

2019 · arXiv (Cornell University)

Stochastic gradient descent requires that training samples be drawn from a uniformly random distribution of the data. For a deployed system that must learn online from an uncontrolled and unknown environment, the ordering of input …

Efficient Data Privacy and Security in Autonomous Cars

2019 · Journal of Computer Sciences and Applications

As the advancement and testing of self-driving auto innovation has advanced, the possibility of exclusive self-ruling vehicles working on open streets is nearing. Industry specialists foresee that self-governing vehicles will be financially accessible inside the …

A study of the performance of embedding methods for Arabic short-text sentiment analysis using deep learning approaches

2021 · Journal of King Saud University - Computer and Information Sciences

Sentiment analysis aims to classify a text according to sentimental polarities of people’s opinions, such as positive, negative, or neutral. While most of the studies focus on eliciting features from English text, the research on …

Continual Learning with Scaled Gradient Projection

2023 · arXiv (Cornell University)

In neural networks, continual learning results in gradient interference among sequential tasks, leading to catastrophic forgetting of old tasks while learning new ones. This issue is addressed in recent methods by storing the important gradient …

Homogenizing Non-IID datasets via In-Distribution Knowledge Distillation for Decentralized Learning

2023 · arXiv (Cornell University)

Decentralized learning enables serverless training of deep neural networks (DNNs) in a distributed manner on multiple nodes. This allows for the use of large datasets, as well as the ability to train with a wide …

Subspace distillation for continual learning

2023 · Neural Networks

An ultimate objective in continual learning is to preserve knowledge learned in preceding tasks while learning new tasks. To mitigate forgetting prior knowledge, we propose a novel knowledge distillation technique that takes into the account …

RDR: the Recap, Deliberate, and Respond Method for Enhanced Language Understanding

2023 · arXiv (Cornell University)

Natural language understanding (NLU) using neural network pipelines often requires additional context that is not solely present in the input data. Through Prior research, it has been evident that NLU benchmarks are susceptible to manipulation …