Improving the Robustness of Quantized Deep Neural Networks to White-Box Attacks using Stochastic Quantization and Information-Theoretic Ensemble Training

no code implementations • 30 Nov 2023 • Saurabh Farkya, Aswin Raghavan, Avi Ziskind

We present a method to improve the robustness of quantized DNNs to white-box adversarial attacks.

Information Plane Quantization

Real-time Hyper-Dimensional Reconfiguration at the Edge using Hardware Accelerators

no code implementations • 10 Jun 2022 • Indhumathi Kandaswamy, Saurabh Farkya, Zachary Daniels, Gooitzen van der Wal, Aswin Raghavan, Yuzheng Zhang, Jun Hu, Michael Lomnitz, Michael Isnardi, David Zhang, Michael Piacentino

In this paper we present Hyper-Dimensional Reconfigurable Analytics at the Tactical Edge (HyDRATE) using low-SWaP embedded hardware that can perform real-time reconfiguration at the edge leveraging non-MAC (free of floating-point MultiplyACcumulate operations) deep neural nets (DNN) combined with hyperdimensional (HD) computing accelerators.

Few-Shot Learning Quantization

Saccade Mechanisms for Image Classification, Object Detection and Tracking

no code implementations • 10 Jun 2022 • Saurabh Farkya, Zachary Daniels, Aswin Nadamuni Raghavan, David Zhang, Michael Piacentino

We examine how the saccade mechanism from biological vision can be used to make deep neural networks more efficient for classification and object detection problems.

Classification Image Classification +4