Accepted Papers

  • GA3C: GPU-based A3C for Deep Reinforcement Learning
    Mohammad Babaeizadeh, University of Illinois at Urbana-Champaign; Iuri Frosio, NVIDIA; Stephen Tyree, NVIDIA; Jason Clemons, NVIDIA; Kautz Jan, NVIDIA Oral
  • Deep Roots: Improving CNN Efficiency with Hierarchical Filter Groups
    Yani Ioannou, University of Cambridge; Duncan Robertson, Microsoft; Roberto Cipolla, University of Cambridge; Antonio Criminisi, Microsoft Poster
  • Evolutionary Synthesis of Deep Neural Networks via Synaptic Cluster-driven Genetic Encoding
    Mohammad Javad Shafiee, University of Waterloo; Alexander Wong, University of Waterloo Oral
  • A Binary Convolutional Encoder-decoder Network for Real-time Natural Scene Text Processing
    Zichuan Liu, Nanyang Technological University; Yixing Li, Arizona State University; Hao Yu, Nanyang Technological University; Fengbo Ren, Arizona State University Oral
  • Compacting Neural Network Classifiers via Dropout Training
    Yotaro Kubo, Amazon; George Tucker, Google Brain; Simon Wiesler, Amazon Poster
  • Parallelizing Word2Vec in Multi-Core and Many-Core Architectures
    Shihao Ji, Intel Labs; Nadathur Rajagopalan Satish, Intel Labs; Sheng Li, Intel Labs; Pradeep Dubey, Intel Labs Poster
  • Ternary weight networks
    Fengfu Li, LSEC and Institute of Applied Mathematics, AMSS, Chinese Academy of Sciences Poster
  • Quantized neural network design under weight capacity constraint
    Sungho Shin, Seoul National University; Kyuyeon Hwang, Seoul National University; Wonyong Sung, Seoul National University Poster
  • Pruning Convolutional Neural Networks for Resource Efficient Transfer Learning
    Pavlo Molchanov, NVIDIA; Stephen Tyree, NVIDIA; Tero Karras, NVidia; Timo Aila, NVIDIA Research; Kautz Jan, NVIDIA Poster
  • PVANET: Lightweight Neural Networks for Real-time Object Detection
    Sanghoon Hong, Intel; Byungseok Roh, Intel; Kye-Hyeon Kim, SK T-brain; Yeongjae Cheon, Intel; Minje Park, Intel Oral
  • Recurrent Neural Networks With Limited Numerical Precision
    Joachim Ott, ETH Zurich Oral
  • Efficient Stochastic Inference of Bitwise Deep Neural Networks
    Sebastian Vogel, Robert Bosch GmbH; Christoph Schorn, Robert Bosch GmbH; Andre Guntoro, Robert Bosch GmbH; Gerd Ascheid, RWTH Aachen University Poster
  • Quantized Neural Networks
    Itay Hubara, Technion; Matthieu Courbariaux, universite de montreal; Daniel Soudry, Columbia University; Ran El-Yaniv, Technion; Yoshua Bengio, Universite de Montreal Poster
  • NoiseOut: A Simple Way to Prune Neural Networks
    Mohammad Babaeizadeh, University of Illinois at Urbana-Champaign; Paris Smaragdis, University of Illinois at Urbana-Champaign; Roy Campbell, University of Illinois at Urbana-Champaign Poster
  • Pruning Filters for Efficient ConvNets
    Hao Li, University of Maryland, College Park; Asim Kadav, NEC Labs; Igor Durdanovic, NEC Labs; Hanan Samet, University of Maryland, College Park; Hans Peter Graf, NEC Labs Poster
  • dMath: Distributed Linear Algebra for DL
    Steven Eliuk, Samsung Electronics; Cameron Upright, Samsung; Hars Vardhan, Samsung; Trevor Gale, Samsung Intern / Northestern University; Stephen Walsh, Samsung Intern / University of Alberta Poster
  • AdaNet: Adaptive Structural Learning of Artificial Neural Networks
    Javier Gonzalvo, Google; Vitaly Kuznetsov, Google; Corinna Cortes, Google; Mehryar Mohri, Courant Institute; Scott Yang, Courant Institute of Mathematical Sciences Poster
  • Efficient Convolutional Auto-Encoding via Random Convexification and Frequency-Domain Minimization
    Meshia C├ędric Oveneke, Vrije Universiteit Brussel; Mitchel Perez Gonzalez, Vrije Universiteit Brussel; Yong Zhao, Vrije Universiteit Brussel; Dongmei Jiang, Northwestern Polytechnical University; Hichem Sahli, Vrije Universiteit Brussel Poster
  • Efficient Convolutional Neural Network with Binary Quantization Layer
    Mahdyar Ravanbakhsh, University of Genova; Hossein mousavi, Istituto Italiano di Tecnologia; Moin Nabi, University of Trento; LUCIO MARCENARO, Universita degli Studi di Genoa, Genoa; CARLO REGAZZONI, University of Genova, Italy Poster
  • Binarized Neural Networks on the ImageNet Classification Task
    Xundong Wu, UCLA; Yong Wu, UCLA; Yong Zhao, Peking University Poster
  • Compression of Deep Convolutional Neural Networks for Fast and Low Power Mobile Applications
    Yong-Deok Kim, Samsung Electronics; Sungjoo Yoo, Seoul National University; Eunhyeok Park, Seoul National University Poster
  • ESE: Efficient Speech Recognition Engine with Compressed LSTM on FPGA
    Song Han, Stanford University; Junlong Kang, Deephi; Huizi Mao, Stanford University; Yiming Hu, Tsinghua Unviersity; Xin Li, Deephi; Yubin Li, Deephi; Dongliang Xie, Deephi; Hong Luo, Deephi; Song Yao, Deephi; Huazhong Yang, Tsinghua University; Bill Dally, Stanford University Oral