Sparse: Sparse architecture search for cnns on resource-constrained microcontrollers

I Fedorov, RP Adams, M Mattina… - Advances in Neural …, 2019 - proceedings.neurips.cc
The vast majority of processors in the world are actually microcontroller units (MCUs), which
find widespread use performing simple control tasks in applications ranging from …

Entropy-driven mixed-precision quantization for deep network design

Z Sun, C Ge, J Wang, M Lin, H Chen… - Advances in Neural …, 2022 - proceedings.neurips.cc
Deploying deep convolutional neural networks on Internet-of-Things (IoT) devices is
challenging due to the limited computational resources, such as limited SRAM memory and …

Leaky nets: Recovering embedded neural network models and inputs through simple power and timing side-channels—Attacks and defenses

S Maji, U Banerjee… - IEEE Internet of Things …, 2021 - ieeexplore.ieee.org
With the recent advancements in machine learning theory, many commercial embedded
microprocessors use neural network (NN) models for a variety of signal processing …

RNNPool: Efficient non-linear pooling for RAM constrained inference

O Saha, A Kusupati, HV Simhadri… - Advances in Neural …, 2020 - proceedings.neurips.cc
Abstract Standard Convolutional Neural Networks (CNNs) designed for computer vision
tasks tend to have large intermediate activation maps. These require large working memory …

A threshold implementation-based neural network accelerator with power and electromagnetic side-channel countermeasures

S Maji, U Banerjee, SH Fuller… - IEEE Journal of Solid …, 2022 - ieeexplore.ieee.org
With the recent advancements in machine learning (ML) theory, a lot of energy-efficient
neural network (NN) accelerators have been developed. However, their associated side …

Neural network for low-memory IoT devices and MNIST image recognition using kernels based on logistic map

A Velichko - Electronics, 2020 - mdpi.com
This study presents a neural network which uses filters based on logistic mapping
(LogNNet). LogNNet has a feedforward network structure, but possesses the properties of …

Resot: Resource-efficient oblique trees for neural signal classification

B Zhu, M Farivar, M Shoaran - IEEE Transactions on …, 2020 - ieeexplore.ieee.org
Classifiers that can be implemented on chip with minimal computational and memory
resources are essential for edge computing in emerging applications such as medical and …

Rethinking generalization in american sign language prediction for edge devices with extremely low memory footprint

AJ Paul, P Mohan, S Sehgal - 2020 IEEE Recent Advances in …, 2020 - ieeexplore.ieee.org
Due to the boom in technical compute in the last few years, the world has seen massive
advances in artificially intelligent systems solving diverse real-world problems. But a major …

A method for medical data analysis using the LogNNet for clinical decision support systems and edge computing in healthcare

A Velichko - Sensors, 2021 - mdpi.com
Edge computing is a fast-growing and much needed technology in healthcare. The problem
of implementing artificial intelligence on edge devices is the complexity and high resource …

An energy-efficient neural network accelerator with improved resilience against fault attacks

S Maji, K Lee, C Gongye, Y Fei… - IEEE Journal of Solid …, 2024 - ieeexplore.ieee.org
Embedded neural network (NN) implementations are vulnerable to misclassification under
fault attacks (FAs). Clock glitching and injecting strong electromagnetic (EM) pulses are two …