• Publications
  • Influence
Recurrent Residual Convolutional Neural Network based on U-Net (R2U-Net) for Medical Image Segmentation
We propose a Recurrent Convolutional Neural Network (RCNN) based on U-Net, Residual Network, as well as R2U-Net models, which are named RU-Net and R2u-Net respectively. Expand
  • 157
  • 23
  • Open Access
Generalized Memristive Device SPICE Model and its Application in Circuit Design
This paper presents a SPICE model for memristive devices. It builds on existing models and is correlated against several published device characterization data with an average error of 6.04%. WhenExpand
  • 132
  • 20
  • Open Access
The History Began from AlexNet: A Comprehensive Survey on Deep Learning Approaches
Deep learning has demonstrated tremendous success in variety of application domains in the past few years. Expand
  • 192
  • 18
  • Open Access
A Memristor Device Model
This letter proposes a new mathematical model for memristor devices. It builds on existing models and is correlated against several published device characterizations. This letter identifiesExpand
  • 183
  • 11
  • Open Access
Enabling back propagation training of memristor crossbar neuromorphic processors
  • R. Hasan, T. Taha
  • Computer Science
  • International Joint Conference on Neural Networks…
  • 6 July 2014
This paper presents circuits to train a cascaded set of memristor crossbars representing a multi-layered neural network. Expand
  • 67
  • 6
FPGA Implementation of Izhikevich Spiking Neural Networks for Character Recognition
We developed a modularized processing element to evaluate a large number of Izhikevich spiking neurons in a pipelined manner. Expand
  • 77
  • 5
  • Open Access
A State-of-the-Art Survey on Deep Learning Theory and Architectures
In recent years, deep learning has garnered tremendous success in a variety of application domains. This new field of machine learning has been growing rapidly and has been applied to mostExpand
  • 112
  • 4
Intrusion detection using deep belief networks
With the advent of digital technology, security threats for computer networks have increased dramatically over the last decade being much bolder and brazen. There is a great need for an effectiveExpand
  • 101
  • 4
Memristor crossbar deep network implementation based on a Convolutional neural network
This paper presents a simulated memristor crossbar implementation of a deep Convolutional Neural Network (CNN). Expand
  • 48
  • 4
Neuromorphic models on a GPGPU cluster
  • B. Han, T. Taha
  • Computer Science
  • The International Joint Conference on Neural…
  • 18 July 2010
This paper examines the feasibility of using a cluster of NVIDIA General Purpose Graphics Processing Units (GPGPUs) for accelerating a spiking neural network based character recognition network based on the Izhikevich and Hodgkin-Huxley models to enable such large scale systems. Expand
  • 26
  • 4