3 citations · 3 across the 1 of their papers we have counts for
6 papers
Textless NLP -- Zero Resource Challenge with Low Resource Compute
Krithiga Ramadass, Abrit Pal Singh, Srihari J +1
This work addresses the persistent challenges of substantial training time and GPU resource requirements even when training lightweight encoder-vocoder models for Textless NLP. We…
Golden Ratio Search: A Low-Power Adversarial Attack for Deep Learning based Modulation Classification
Deepsayan Sadhukhan, Nitin Priyadarshini Shankar, Sheetal Kalyani
We propose a minimal power white box adversarial attack for Deep Learning based Automatic Modulation Classification (AMC). The proposed attack uses the Golden Ratio Search (GRS) me…
Learning Rate Optimization for Deep Neural Networks Using Lipschitz Bandits
Padma Priyanka, Sheetal Kalyani, Avhishek Chatterjee
Learning rate is a crucial parameter in training of neural networks. A properly tuned learning rate leads to faster training and higher test accuracy. In this paper, we propose a L…
First line of defense: A robust first layer mitigates adversarial attacks
Janani Suresh, Nancy Nayak, Sheetal Kalyani
Adversarial training (AT) incurs significant computational overhead, leading to growing interest in designing inherently robust architectures. We demonstrate that a carefully desig…
Product and Ratio of Two Shadowed Random Variables and its Application to Wireless Communication
Shashank Shekhar, Sheetal Kalyani
This work studies the product and ratio statistics of independent and non-identically distributed (i.n.i.d) shadowed random variables. We derive the series expression for…
Max-Min Data Rate Optimization for RIS-aided Uplink Communications with Green Constraints
Athira Subhash, Abla Kammoun, Ahmed Elzanaty +3
Smart radio environments aided by reconfigurable intelligent reflecting surfaces (RIS) have attracted much research attention recently. We propose a joint optimization strategy for…