no code implementations • 1 Jun 2022 • Nancy Nayak, Sheetal Kalyani
We show that this activation wherein the rotation is learned via training results in the elimination of those parameters/filters in the network which are not important for the task.
no code implementations • 27 Oct 2021 • Deepsayan Sadhukhan, Nitin Priyadarshini Shankar, Nancy Nayak, Thulasi Tholeti, Sheetal Kalyani
The proposed MC method with RBLResNets has an adversarial accuracy of $87. 25\%$ over a wide range of SNRs, surpassing the robustness of all existing SOTA methods to the best of our knowledge.
no code implementations • 15 Oct 2021 • Akshay Sharma, Nancy Nayak, Sheetal Kalyani
The proposed method achieves $92\%$ accuracy in a channel of noise variance $10^{-6}$ with $19. 3\%$ of the brute-force method's computation.
no code implementations • 13 Jun 2020 • Vishnu Raj, Nancy Nayak, Sheetal Kalyani
Compact neural networks are essential for affordable and power efficient deep learning solutions.
no code implementations • 20 Mar 2020 • Nancy Nayak, Thulasi Tholeti, Muralikrishnan Srinivasan, Sheetal Kalyani
This paper introduces an incremental training framework for compressing popular Deep Neural Network (DNN) based unfolded multiple-input-multiple-output (MIMO) detection algorithms like DetNet.
no code implementations • 25 Jan 2020 • Vishnu Raj, Nancy Nayak, Sheetal Kalyani
Directional beamforming is a crucial component for realizing robust wireless communication systems using millimeter wave (mmWave) technology.