skip to main content

Search for: All records

Creators/Authors contains: "Jaiswal, Akhilesh"

Note: When clicking on a Digital Object Identifier (DOI) number, you will be taken to an external site maintained by the publisher. Some full text articles may not yet be available without a charge during the embargo (administrative interval).
What is a DOI Number?

Some links on this page may take you to non-federal websites. Their policies may differ from this site.

  1. Quantum computers provide faster solutions to specific compute-intensive classical problems. However, building a fault-tolerant quantum computer architecture is challenging and demands integrating several qubits with optimized signal routing while maintaining its quantum coherence. Experimental realization of such quantum computers with diverse functional components in a planar monolithic device architecture is challenging due to material and thermodynamic mismatch between various elements. Furthermore, it requires complex control and routing, resulting in parasitic modes and reduced qubit coherence. Thus, a scalable interposer architecture is essential to merge and interconnect different functionalities within a sophisticated chip while maintaining qubit coherence. As such, heterogeneous integration is an optimum solution to scale the qubit technology. We propose a heterogeneously integrated quantum chip optoelectronics interposer as a solution to the high-density scalable qubit architecture. Our technology is high-volume manufacturable and provides novel optical I/O solutions for on-chip, chip-to-chip, and cryogenic-to-outside world interconnect. 
    more » « less
  2. High-quality 3D image recognition is an important component of many vision and robotics systems. However, the accurate processing of these images requires the use of compute-expensive 3D Convolutional Neural Networks (CNNs). To address this challenge, we propose the use of Spiking Neural Networks (SNNs) that are generated from iso-architecture CNNs and trained with quantization-aware gradient descent to optimize their weights, membrane leak, and firing thresholds. During both training and inference, the analog pixel values of a 3D image are directly applied to the input layer of the SNN without the need to convert to a spike-train. This significantly reduces the training and inference latency and results in high degree of activation sparsity, which yields significant improvements in computational efficiency. However, this introduces energy-hungry digital multiplications in the first layer of our models, which we propose to mitigate using a processing-in-memory (PIM) architecture. To evaluate our proposal, we propose a 3D and a 3D/2D hybrid SNN-compatible convolutional architecture and choose hyperspectral imaging (HSI) as an application for 3D image recognition. We achieve overall test accuracy of 98.68, 99.50, and 97.95% with 5 time steps (inference latency) and 6-bit weight quantization on the Indian Pines, Pavia University, and Salinas Scene datasets, respectively. In particular, our models implemented using standard digital hardware achieved accuracies similar to state-of-the-art (SOTA) with ~560.6× and ~44.8× less average energy than an iso-architecture full-precision and 6-bit quantized CNN, respectively. Adopting the PIM architecture in the first layer, further improves the average energy, delay, and energy-delay-product (EDP) by 30, 7, and 38%, respectively. 
    more » « less