Výsledky vyhledávání - "Fraser, Nicholas J."

Report

Ps and Qs: Quantization-aware pruning for efficient low latency neural network inference

Autor: Hawks, Benjamin, Duarte, Javier, Fraser, Nicholas J., Pappalardo, Alessandro, Tran, Nhan, Umuroglu, Yaman

Publikováno v: Front. AI 4, 94 (2021)

Efficient machine learning implementations optimized for inference in hardware have wide-ranging benefits, depending on the application, from lower inference latency to higher data throughput and reduced energy consumption. Two popular techniques for

Externí odkaz: http://arxiv.org/abs/2102.11289

Zobrazit plný text záznamu

Report

FAT: Training Neural Networks for Reliable Inference Under Hardware Faults

Autor: Zahid, Ussama, Gambardella, Giulio, Fraser, Nicholas J., Blott, Michaela, Vissers, Kees

Deep neural networks (DNNs) are state-of-the-art algorithms for multiple applications, spanning from image classification to speech recognition. While providing excellent accuracy, they often have enormous compute and memory requirements. As a result

Externí odkaz: http://arxiv.org/abs/2011.05873

Zobrazit plný text záznamu

Report

LogicNets: Co-Designed Neural Networks and Circuits for Extreme-Throughput Applications

Autor: Umuroglu, Yaman, Akhauri, Yash, Fraser, Nicholas J., Blott, Michaela

Deployment of deep neural networks for applications that require very high throughput or extremely low latency is a severe computational challenge, further exacerbated by inefficiencies in mapping the computation to hardware. We present a novel metho

Externí odkaz: http://arxiv.org/abs/2004.03021

Zobrazit plný text záznamu

Report

Accuracy to Throughput Trade-offs for Reduced Precision Neural Networks on Reconfigurable Logic

Autor: Su, Jiang, Fraser, Nicholas J., Gambardella, Giulio, Blott, Michaela, Durelli, Gianluca, Thomas, David B., Leong, Philip, Cheung, Peter Y. K.

Modern CNN are typically based on floating point linear algebra based implementations. Recently, reduced precision NN have been gaining popularity as they require significantly less memory and computational resources compared to floating point. This

Externí odkaz: http://arxiv.org/abs/1807.10577

Zobrazit plný text záznamu

Report

Scaling Binarized Neural Networks on Reconfigurable Logic

Autor: Fraser, Nicholas J., Umuroglu, Yaman, Gambardella, Giulio, Blott, Michaela, Leong, Philip, Jahre, Magnus, Vissers, Kees

Binarized neural networks (BNNs) are gaining interest in the deep learning community due to their significantly lower computational and memory cost. They are particularly well suited to reconfigurable logic devices, which contain an abundance of fine

Externí odkaz: http://arxiv.org/abs/1701.03400

Zobrazit plný text záznamu

Report

FINN: A Framework for Fast, Scalable Binarized Neural Network Inference

Autor: Umuroglu, Yaman, Fraser, Nicholas J., Gambardella, Giulio, Blott, Michaela, Leong, Philip, Jahre, Magnus, Vissers, Kees

Research has shown that convolutional neural networks contain significant redundancy, and high classification accuracy can be obtained even when weights and activations are reduced from floating point to binary values. In this paper, we present FINN,

Externí odkaz: http://arxiv.org/abs/1612.07119

Zobrazit plný text záznamu