Efficient Hybrid Network Architectures for Extremely Quantized Neural Networks Enabling Intelligence at the Edge

Generalization by weight-elimination with application to forecasting

Weigend et al · 1991

Earlier work this paper cites.

Learning multiple layers of features from tiny images

Krizhevsky and Hinton · 2009

Earlier work this paper cites.

Imagenet: A large-scale hierarchical image database

Deng et al · 2009

Earlier work this paper cites.

Gpus and the future of parallel computing

Keckler et al · 2011

Earlier work this paper cites.

Imagenet classification with deep convolutional neural networks

Krizhevsky et al · 2012

Earlier work this paper cites.

Efficient estimation of word representations in vector space

Mikolov et al · 2013

Earlier work this paper cites.

Going deeper with convolutions

Szegedy et al · 2015

Earlier work this paper cites.

Fast r-cnn

Girshick et al · 2015

Cited alongside, same era.

Human-level control through deep reinforcement learning

Mnih et al · 2015

Cited alongside, same era.

Learning both weights and connections for efficient neural network

Han et al · 2015

Cited alongside, same era.

Deep residual learning for image recognition

He et al · 2016

Cited alongside, same era.

Squeezenet: Alexnet-level accuracy with 50x fewer parameters and< 0.5 mb model size

Original

Iandola et al · 2016

Cited alongside, same era.

Xnor-net: Imagenet classification using binary convolutional neural networks

Rastegari et al · 2016

Cited alongside, same era.

Mastering the game of go without human knowledge

Silver et al · 2017

Later among the works it cites.

Compression-aware training of deep networks

Alvarez and Salzmann · 2017

Later among the works it cites.

Soft weight-sharing for neural network compression

Original

Ullrich et al · 2017

Later among the works it cites.

Quantized neural networks: Training neural networks with low precision weights and activations

Hubara et al · 2017

Later among the works it cites.

Ternary neural networks with fine-grained quantization

Original

Mellempudi et al · 2017

Later among the works it cites.

Hybrid binary networks: Optimizing for accuracy, efficiency and memory