Using transfer learning approach to implement convolutional neural network model to recommend airline tickets by using online reviews

M Heidari, S Rafatirad - 2020 15th International Workshop on …, 2020 - ieeexplore.ieee.org
Social Media provides an opportunity for people to share their idea about different aspects of
life. Traveling is one of the essential aspects of life. In this paper, we use Bidirectional …

Bidirectional transformer based on online text-based information to implement convolutional neural network model for secure business investment

M Heidari, S Rafatirad - 2020 IEEE International Symposium on …, 2020 - ieeexplore.ieee.org
Real estate investment decisions are critical for low-income people who have just one home
as their life-time investment option. So during the COVID-19 pandemic, unemployment …

Code-bridged classifier (cbc): A low or negative overhead defense for making a cnn classifier robust against adversarial attacks

F Behnia, A Mirzaeian, M Sabokrou… - … on Quality Electronic …, 2020 - ieeexplore.ieee.org
In this paper, we propose Code-Bridged Classifier (CBC), a framework for making a
Convolutional Neural Network (CNNs) robust against adversarial attacks without increasing …

Analysis of a pipelined architecture for sparse DNNs on embedded systems

AA Moreno, J Olivito, J Resano… - IEEE Transactions on …, 2020 - ieeexplore.ieee.org
Deep neural networks (DNNs) are increasing their presence in a wide range of applications,
and their computationally intensive and memory-demanding nature poses challenges …

Diverse knowledge distillation (dkd): A solution for improving the robustness of ensemble models against adversarial attacks

A Mirzaeian, J Kosecka, H Homayoun… - … on Quality Electronic …, 2021 - ieeexplore.ieee.org
This paper proposes an ensemble learning model that is resistant to adversarial attacks. To
build resilience, we introduced a training process where each member learns a radically …

Nesta: Hamming weight compression-based neural proc. engineali mirzaeian

A Mirzaeian, H Homayoun… - 2020 25th Asia and South …, 2020 - ieeexplore.ieee.org
In this paper, we present NESTA, a specialized Neural engine that significantly accelerates
the computation of convolution layers in a deep convolutional neural network, while …

Binary precision neural network manycore accelerator

M Hosseini, T Mohsenin - ACM Journal on Emerging Technologies in …, 2021 - dl.acm.org
This article presents a low-power, programmable, domain-specific manycore accelerator,
Binarized neural Network Manycore Accelerator (BiNMAC), which adopts and efficiently …

A survey on recent hardware data prefetching approaches with an emphasis on servers

M Bakhshalipour, M Shakerinava, F Golshan… - arXiv preprint arXiv …, 2020 - arxiv.org
Data prefetching, ie, the act of predicting application's future memory accesses and fetching
those that are not in the on-chip caches, is a well-known and widely-used approach to hide …

Conditional classification: A solution for computational energy reduction

A Mirzaeian, S Manoj, A Vakil… - … on Quality Electronic …, 2021 - ieeexplore.ieee.org
Deep convolutional neural networks have shown high efficiency in computer visions and
other applications. However, with the increase in the depth of the networks, the …

[PDF][PDF] Learning diverse latent representations for improving the resilience to adversarial attacks

A Mirzaeian, M Sabokrou, M Khalooei… - arXiv e-prints, pp …, 2020 - academia.edu
This paper proposes an ensemble learning model that is resistant to adversarial learning
attacks. To build resilience, we proposed a training process where each member learns a …