22 citations · 87 across the 18 of their papers we have counts for
18 papers
On the Robustness of Randomized Ensembles to Adversarial Perturbations
Hassan Dbouk, Naresh R. Shanbhag
Randomized ensemble classifiers (RECs), where one classifier is randomly selected during inference, have emerged as an attractive alternative to traditional ensembling methods for…
Coordinated Science Laboratory 70th Anniversary Symposium: The Future of Computing
Klara Nahrstedt, Naresh Shanbhag, Vikram Adve +25
In 2021, the Coordinated Science Laboratory CSL, an Interdisciplinary Research Unit at the University of Illinois Urbana-Champaign, hosted the Future of Computing Symposium to cele…
Adversarial Vulnerability of Randomized Ensembles
Hassan Dbouk, Naresh R. Shanbhag
Despite the tremendous success of deep neural networks across various tasks, their vulnerability to imperceptible adversarial perturbations has hindered their deployment in the rea…
Generalized Depthwise-Separable Convolutions for Adversarially Robust and Efficient Neural Networks
Hassan Dbouk, Naresh R. Shanbhag
Despite their tremendous successes, convolutional neural networks (CNNs) incur high computational/storage costs and are vulnerable to adversarial perturbations. Recent works on rob…
Robustifying Adversarial Training to the Union of Perturbation Models
Ameya D. Patil, Michael Tuttle, Alexander G. Schwing +1
Classical adversarial training (AT) frameworks are designed to achieve high adversarial accuracy against a single attack type, typically norm-bounded perturbations. R…
Fundamental Limits on Energy-Delay-Accuracy of In-memory Architectures in Inference Applications
Sujan Kumar Gonugondla, Charbel Sakr, Hassan Dbouk +1
This paper obtains fundamental limits on the computational precision of in-memory computing architectures (IMCs). An IMC noise model and associated SNR metrics are defined and thei…
DBQ: A Differentiable Branch Quantizer for Lightweight Deep Neural Networks
Hassan Dbouk, Hetul Sanghvi, Mahesh Mehendale +1
Deep neural networks have achieved state-of-the art performance on various computer vision tasks. However, their deployment on resource-constrained devices has been hindered due to…
Nanotechnology-inspired Information Processing Systems of the Future
Randy Bryant, Mark Hill, Tom Kazior +9
Nanoscale semiconductor technology has been a key enabler of the computing revolution. It has done so via advances in new materials and manufacturing processes that resulted in the…
HarDNN: Feature Map Vulnerability Evaluation in CNNs
Abdulrahman Mahmoud, Siva Kumar Sastry Hari, Christopher W. Fletcher +7
As Convolutional Neural Networks (CNNs) are increasingly being employed in safety-critical applications, it is important that they behave reliably in the face of hardware errors. T…
Accumulation Bit-Width Scaling For Ultra-Low Precision Training Of Deep Networks
Charbel Sakr, Naigang Wang, Chia-Yu Chen +4
Efforts to reduce the numerical precision of computations in deep learning training have yielded systems that aggressively quantize weights and activations, yet employ wide high-pr…
Per-Tensor Fixed-Point Quantization of the Back-Propagation Algorithm
Charbel Sakr, Naresh Shanbhag
The high computational and parameter complexity of neural networks makes their training very slow and difficult to deploy on energy and storage-constrained computing systems. Many…
Generalized Water-filling for Source-aware Energy-efficient SRAMs
Yongjune Kim, Mingu Kang, Lav R. Varshney +1
Conventional low-power static random access memories (SRAMs) reduce read energy by decreasing the bit-line voltage swings uniformly across the bit-line columns. This is because the…
Shannon-inspired Statistical Computing to Enable Spintronics
Ameya D. Patil, Sasikanth Manipatruni, Dmitri Nikonov +2
Modern computing systems based on the von Neumann architecture are built from silicon complementary metal oxide semiconductor (CMOS) transistors that need to operate under practica…
Energy-efficient Machine Learning in Silicon: A Communications-inspired Approach
Naresh R. Shanbhag
This position paper advocates a communications-inspired approach to the design of machine learning systems on energy-constrained embedded `always-on' platforms. The communications-…
A 481pJ/decision 3.4M decision/s Multifunctional Deep In-memory Inference Processor using Standard 6T SRAM Array
Mingu Kang, Sujan Gonugondla, Ameya Patil +1
This paper describes a multi-functional deep in-memory processor for inference applications. Deep in-memory processing is achieved by embedding pitch-matched low-SNR analog process…
Understanding the Energy and Precision Requirements for Online Learning
Charbel Sakr, Ameya Patil, Sai Zhang +2
It is well-known that the precision of data, hyperparameters, and internal representations employed in learning systems directly impacts its energy, throughput, and latency. The pr…
Error-Resilient Machine Learning in Near Threshold Voltage via Classifier Ensemble
Sai Zhang, Naresh Shanbhag
In this paper, we present the design of error-resilient machine learning architectures by employing a distributed machine learning framework referred to as classifier ensemble (CE)…
Reducing the Energy Cost of Inference via In-sensor Information Processing
Sai Zhang, Mingu Kang, Charbel Sakr +1
There is much interest in incorporating inference capabilities into sensor-rich embedded platforms such as autonomous vehicles, wearables, and others. A central problem in the desi…