Heterogeneous Bitwidth Binarization in Convolutional Neural Networks

no code implementations • ICLR 2018 • Josh Fromm, Shwetak Patel, Matthai Philipose

Recent work has shown that fast, compact low-bitwidth neural networks can be surprisingly accurate.

Binarization

Focus: Querying Large Video Datasets with Low Latency and Low Cost

no code implementations • 10 Jan 2018 • Kevin Hsieh, Ganesh Ananthanarayanan, Peter Bodik, Paramvir Bahl, Matthai Philipose, Phillip B. Gibbons, Onur Mutlu

Focus handles the lower accuracy of the cheap CNNs by judiciously leveraging expensive CNNs at query-time.

Fast Video Classification via Adaptive Cascading of Deep Models

no code implementations • CVPR 2017 • Haichen Shen, Seungyeop Han, Matthai Philipose, Arvind Krishnamurthy

Recent advances have enabled "oracle" classifiers that can classify across many classes and input distributions with high accuracy without retraining.

Classification Decision Making +2

Do Deep Convolutional Nets Really Need to be Deep and Convolutional?

2 code implementations • 17 Mar 2016 • Gregor Urban, Krzysztof J. Geras, Samira Ebrahimi Kahou, Ozlem Aslan, Shengjie Wang, Rich Caruana, Abdel-rahman Mohamed, Matthai Philipose, Matt Richardson

Yes, they do.

Blending LSTMs into CNNs

no code implementations • 19 Nov 2015 • Krzysztof J. Geras, Abdel-rahman Mohamed, Rich Caruana, Gregor Urban, Shengjie Wang, Ozlem Aslan, Matthai Philipose, Matthew Richardson, Charles Sutton

We consider whether deep convolutional networks (CNNs) can represent decision functions with similar accuracy as recurrent networks such as LSTMs.

Automatic Speech Recognition Automatic Speech Recognition (ASR) +3