Search Results for author:
Found 14 papers, 2 papers with code
Pruning for Improved ADC Efficiency in Crossbar-based Analog In-memory Accelerators
sparsity is then achieved by regularizing the variance of $L_{0}$ norms of neighboring columns within the same crossbar.
WWW: What, When, Where to Compute-in-Memory
The proposed work provides insights into what type of CiM to use, and when and where to optimally integrate it in the cache hierarchy for GEMM acceleration.
On the Noise Stability and Robustness of Adversarially Trained Networks on NVM Crossbars
First, we study the noise stability of such networks on unperturbed inputs and observe that internal activations of adversarially trained networks have lower Signal-to-Noise Ratio (SNR), and are sensitive to noise compared to vanilla networks.
Complexity-aware Adaptive Training and Inference for Edge-Cloud Distributed AI Systems
Only data with high probabilities of belonging to hard classes would be sent to the extension block for prediction.
NAX: Co-Designing Neural Network and Hardware Architecture for Memristive Xbar based Computing Systems
The hardware efficiency (energy, latency and area) as well as application accuracy (considering device and circuit non-idealities) of DNNs mapped to such hardware are co-dependent on network parameters, such as kernel size, depth etc.
Kundt geometries and memory effects in the Brans-Dicke theory of gravity
For other $\omega$ (in the presence of $J$ or without), numerically obtained geodesics lead to results on displacement memory which appear to match qualitatively with those found from a deviation analysis.
General Relativity and Quantum Cosmology High Energy Physics - Theory
On the Intrinsic Robustness of NVM Crossbars Against Adversarial Attacks
The increasing computational demand of Deep Learning has propelled research in special-purpose inference accelerators based on emerging non-volatile memory (NVM) technologies.
Conditionally Deep Hybrid Neural Networks Across Edge and Cloud
The proposed network can be deployed in a distributed manner, consisting of quantized layers and early exits at the edge and full-precision layers on the cloud.
Memory effects in Kundt wave spacetimes
For constant negative curvature, we find there is permanent change in the separation of geodesics after the pulse has departed.
General Relativity and Quantum Cosmology
IMAC: In-memory multi-bit Multiplication andACcumulation in 6T SRAM Array
`In-memory computing' is being widely explored as a novel computing paradigm to mitigate the well known memory bottleneck.
GENIEx: A Generalized Approach to Emulating Non-Ideality in Memristive Xbars using Neural Networks
Further, using the functional simulator and GENIEx, we demonstrate that an analytical model can overestimate the degradation in classification accuracy by $\ge 10\%$ on CIFAR-100 and $3. 7\%$ on ImageNet datasets compared to GENIEx.
Emerging Technologies
Constructing Energy-efficient Mixed-precision Neural Networks through Principal Component Analysis for Edge Intelligence
The `Internet of Things' has brought increased demand for AI-based edge computing in applications ranging from healthcare monitoring systems to autonomous vehicles.
Discretization based Solutions for Secure Machine Learning against Adversarial Attacks
Specifically, discretizing the input space (or allowed pixel levels from 256 values or 8-bit to 4 values or 2-bit) extensively improves the adversarial robustness of DLNs for a substantial range of perturbations for minimal loss in test accuracy.
Efficient Hybrid Network Architectures for Extremely Quantized Neural Networks Enabling Intelligence at the Edge
In this work, we propose extremely quantized hybrid network architectures with both binary and full-precision sections to emulate the classification performance of full-precision networks while ensuring significant energy efficiency and memory compression.
