Maedeh Hemmat

University of Wisconsin–Madison | UW · Department of Electrical and Computer Engineering

We propose a framework for Class-aware Personalized Neural Network Inference (CAP’NN), which prunes an already-trained neural network model based on the preferences of individual users. Specifically, by adapting to the subset of output classes that each user is expected to encounter, CAP’NN is able to prune not only ineffectual neurons but also mis...

In this work, we propose AirNN, a novel framework which enables dynamic approximation of an already-trained Convolutional Neural Network (CNN) in hardware during inference. AirNN enables input-dependent approximation of the CNN to achieve energy saving without much degradation in its classification accuracy at run-time. For each input, AirNN uses o...

This is the first work to propose a co-design approach for generation of the network model of a convolutional neural network (CNN) and its implementation using the ReRAM technology to achieve power efficiency. State-of-the-art in this area is based on implementation of an already fixed CNN model. It uses parallel crossbar structures to achieve a de...

In this work, to improve the timing yield of Tunnel Field Effect Transistor (TFET) circuits in the presence of process variations as well as their soft-error resiliency, we propose replacing some of TFET-based gates by MOSFET-based ones. The effectiveness of the proposed TFET-MOSFET hybrid implementation of the circuits are investigated by first st...

In this paper, the impact of physical parameter variations on the electrical characteristics of III-V TFETs is investigated. The study is performed on the operations of two optimized ultra-thin 20 nm double-gate transistors. The two device structures are InAs homojunction TFET and InAs-GaAs0.1Sb0.9 heterojunction TFET. The operation parameters are...