no code implementations • 30 Jan 2024 • Heath Smith, James Seekings, Mohammadreza Mohammadi, Ramtin Zand
The paper focuses on real-time facial expression recognition (FER) systems as an important component in various real-world applications such as social robotics.
Facial Expression Recognition Facial Expression Recognition (FER)
no code implementations • 17 May 2023 • Joseph Lindsay, Ramtin Zand
Works in quantum machine learning (QML) over the past few years indicate that QML algorithms can function just as well as their classical counterparts, and even outperform them in some cases.
no code implementations • 17 May 2023 • Mohammadreza Mohammadi, Heath Smith, Lareb Khan, Ramtin Zand
Facial Expression Recognition (FER) plays an important role in human-computer interactions and is used in a wide range of applications.
Facial Expression Recognition Facial Expression Recognition (FER)
no code implementations • 18 Apr 2023 • Mohammed E. Elbtity, Brendan Reidy, Md Hasibul Amin, Ramtin Zand
To leverage the strengths of TPUs for convolutional layers and IMAC circuits for dense layers, we propose a unified learning algorithm that incorporates mixed-precision training techniques to mitigate potential accuracy drops when deploying models on the TPU-IMAC architecture.
1 code implementation • 18 Apr 2023 • Md Hasibul Amin, Mohammed E. Elbtity, Ramtin Zand
Thus, in this paper, we develop IMAC-Sim, a circuit-level simulator for the design space exploration of IMAC architectures.
no code implementations • 10 Oct 2022 • Peyton Chandarana, Mohammadreza Mohammadi, James Seekings, Ramtin Zand
In recent years, several edge deep learning hardware accelerators have been released that specifically focus on reducing the power and area consumed by deep neural networks (DNNs).
no code implementations • 2 Oct 2022 • Md Hasibul Amin, Mohammed Elbtity, Ramtin Zand
Conventional in-memory computing (IMC) architectures consist of analog memristive crossbars to accelerate matrix-vector multiplication (MVM), and digital functional units to realize nonlinear vector (NLV) operations in deep neural networks (DNNs).
no code implementations • 25 Jul 2022 • Mohammadreza Mohammadi, Peyton Chandarana, James Seekings, Sara Hendrix, Ramtin Zand
The best DNN model achieves an accuracy of 99. 93% on the ASL Alphabet dataset, whereas the best performing SNN model has an accuracy of 99. 30%.
no code implementations • 21 Apr 2022 • Md Hasibul Amin, Mohammed Elbtity, Mohammadreza Mohammadi, Ramtin Zand
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 inverter.
no code implementations • 29 Jan 2022 • Md Hasibul Amin, Mohammed Elbtity, Ramtin Zand
Fully-analog in-memory computing (IMC) architectures that implement both matrix-vector multiplication and non-linear vector operations within the same memory array have shown promising performance benefits over conventional IMC systems due to the removal of energy-hungry signal conversion units.
no code implementations • 19 Oct 2021 • Peyton Chandarana, Junlin Ou, Ramtin Zand
Herein, we propose a method for encoding static images into temporal spike trains using edge detection and an adaptive signal sampling method for use in SNNs.
no code implementations • 24 May 2021 • Mohammed Elbtity, Abhishek Singh, Brendan Reidy, Xiaochen Guo, Ramtin Zand
In this paper, we develop an in-memory analog computing (IMAC) architecture realizing both synaptic behavior and activation functions within non-volatile memory arrays.
no code implementations • 4 Dec 2020 • Ramtin Zand
In this paper, spin-orbit torque (SOT) magnetoresistive random-access memory (MRAM) devices are leveraged to realize sigmoidal neurons and binarized synapses for a single-cycle analog in-memory computing (IMC) architecture.
no code implementations • 22 Sep 2020 • Brendan Reidy, Golareh Jalilvand, Tengfei Jiang, Ramtin Zand
Results obtained show that the CNN model with optimized complexity, dropout, and data augmentation can achieve a classification accuracy comparable to that of a human expert.
no code implementations • 1 Jun 2020 • Brendan Reidy, Ramtin Zand
In this paper, the intrinsic physical characteristics of spin-orbit torque (SOT) magnetoresistive random-access memory (MRAM) devices are leveraged to realize sigmoidal neurons in neuromorphic architectures.
no code implementations • 8 Jan 2019 • Ramtin Zand, Ronald F. DeMara
In this paper, a spintronic neuromorphic reconfigurable Array (SNRA) is developed to fuse together power-efficient probabilistic and in-field programmable deterministic computing during both training and evaluation phases of restricted Boltzmann machines (RBMs).
no code implementations • 28 Nov 2018 • Ramtin Zand, Kerem Y. Camsari, Supriyo Datta, Ronald F. DeMara
Magnetoresistive random access memory (MRAM) technologies with thermally unstable nanomagnets are leveraged to develop an intrinsic stochastic neuron as a building block for restricted Boltzmann machines (RBMs) to form deep belief networks (DBNs).