23 citations · 63 across the 12 of their papers we have counts for
13 papers
Parameter-Efficient Multimodal Brain Tumor Segmentation With Stage-Wise Shared Adapters
Milad Rostamian, Mohammadreza Mohammadi, Ender Konukoglu +1
Different MRI modalities reveal different parts of a brain tumor. Segmentation models combine information from these modalities to outline tumor regions. Many models use a separate…
CrossNAS: A Cross-Layer Neural Architecture Search Framework for PIM Systems
Md Hasibul Amin, Mohammadreza Mohammadi, Jason D. Bakos +1
In this paper, we propose the CrossNAS framework, an automated approach for exploring a vast, multidimensional search space that spans various design abstraction layers-circuits, a…
Towards Efficient Deployment of Hybrid SNNs on Neuromorphic and Edge AI Hardware
James Seekings, Peyton Chandarana, Mahsa Ardakani +2
This paper explores the synergistic potential of neuromorphic and edge computing to create a versatile machine learning (ML) system tailored for processing data captured by dynamic…
Multi-Objective Neural Architecture Search for In-Memory Computing
Md Hasibul Amin, Mohammadreza Mohammadi, Ramtin Zand
In this work, we employ neural architecture search (NAS) to enhance the efficiency of deploying diverse machine learning (ML) tasks on in-memory computing (IMC) architectures. Init…
Realtime Facial Expression Recognition: Neuromorphic Hardware vs. Edge AI Accelerators
Heath Smith, James Seekings, Mohammadreza Mohammadi +1
The paper focuses on real-time facial expression recognition (FER) systems as an important component in various real-world applications such as social robotics. We investigate two…
Facial Expression Recognition at the Edge: CPU vs GPU vs VPU vs TPU
Mohammadreza Mohammadi, Heath Smith, Lareb Khan +1
Facial Expression Recognition (FER) plays an important role in human-computer interactions and is used in a wide range of applications. Convolutional Neural Networks (CNN) have sho…
Energy-Efficient Deployment of Machine Learning Workloads on Neuromorphic Hardware
Peyton Chandarana, Mohammadreza Mohammadi, James Seekings +1
As the technology industry is moving towards implementing tasks such as natural language processing, path planning, image classification, and more on smaller edge computing devices…
Resisting Deep Learning Models Against Adversarial Attack Transferability via Feature Randomization
Ehsan Nowroozi, Mohammadreza Mohammadi, Pargol Golmohammadi +3
In the past decades, the rise of artificial intelligence has given us the capabilities to solve the most challenging problems in our day-to-day lives, such as cancer prediction and…
Employing Deep Ensemble Learning for Improving the Security of Computer Networks against Adversarial Attacks
Ehsan Nowroozi, Mohammadreza Mohammadi, Erkay Savas +2
In the past few years, Convolutional Neural Networks (CNN) have demonstrated promising performance in various real-world cybersecurity applications, such as network and multimedia…
Static Hand Gesture Recognition for American Sign Language using Neuromorphic Hardware
MohammadReza Mohammadi, Peyton Chandarana, James Seekings +2
In this paper, we develop four spiking neural network (SNN) models for two static American Sign Language (ASL) hand gesture classification tasks, i.e., the ASL Alphabet and ASL Dig…
An Adversarial Attack Analysis on Malicious Advertisement URL Detection Framework
Ehsan Nowroozi, Abhishek, Mohammadreza Mohammadi +1
Malicious advertisement URLs pose a security risk since they are the source of cyber-attacks, and the need to address this issue is growing in both industry and academia. Generally…
MRAM-based Analog Sigmoid Function for In-memory Computing
Md Hasibul Amin, Mohammed Elbtity, Mohammadreza Mohammadi +1
We propose an analog implementation of the transcendental activation function leveraging two spin-orbit torque magnetoresistive random-access memory (SOT-MRAM) devices and a CMOS i…
Quantum N-Boson States and Quantized Motion of Solitonic Droplets: Universal Scaling Properties in Low Dimensions
Jeff Maki, Mohammadreza Mohammadi, Fei Zhou
In this article, we illustrate the scaling properties of a family of solutions for N attractive bosonic atoms in the limit of large . These solutions represent the quantized dyn…