Open AccessPosted Content
To prune, or not to prune: exploring the efficacy of pruning for model compression
Michael H. Zhu,Suyog Gupta +1 more
Reads0
Chats0
TLDR
In this article, the authors investigate two distinct paths for model compression within the context of energy-efficient inference in resource-constrained environments and propose a new gradual pruning technique that is simple and straightforward to apply across a variety of models/datasets with minimal tuning.Abstract:
Model pruning seeks to induce sparsity in a deep neural network's various connection matrices, thereby reducing the number of nonzero-valued parameters in the model. Recent reports (Han et al., 2015; Narang et al., 2017) prune deep networks at the cost of only a marginal loss in accuracy and achieve a sizable reduction in model size. This hints at the possibility that the baseline models in these experiments are perhaps severely over-parameterized at the outset and a viable alternative for model compression might be to simply reduce the number of hidden units while maintaining the model's dense connection structure, exposing a similar trade-off in model size and accuracy. We investigate these two distinct paths for model compression within the context of energy-efficient inference in resource-constrained environments and propose a new gradual pruning technique that is simple and straightforward to apply across a variety of models/datasets with minimal tuning and can be seamlessly incorporated within the training process. We compare the accuracy of large, but pruned models (large-sparse) and their smaller, but dense (small-dense) counterparts with identical memory footprint. Across a broad range of neural network architectures (deep CNNs, stacked LSTM, and seq2seq LSTM models), we find large-sparse models to consistently outperform small-dense models and achieve up to 10x reduction in number of non-zero parameters with minimal loss in accuracy.read more
Citations
More filters
Posted Content
PFGDF: Pruning Filter via Gaussian Distribution Feature for Deep Neural Networks Acceleration
TL;DR: A novel deep learning model compression acceleration method based on data distribution characteristics, namely Pruning Filter via Gaussian Distribution Feature (PFGDF) which was to found the smaller interval of the convolution layer of a certain layer to describe the original on the grounds of distribution characteristics.
Proceedings ArticleDOI
Joint Modeling of Multi-Sample and Subband Signals for Fast Neural Vocoding on CPU
TL;DR: This work proposes a fast and high quality neural vocoder for CPU implementation that real-izes generation with up to four samples without any significant degradation in naturalness and matched the naturalness comparable of the two-sample conventional method.
Journal ArticleDOI
Edge-PRUNE: Flexible Distributed Deep Learning Inference
TL;DR: Compared to previous approaches, Edge-PRUNE is based on a formal dataflow computing model, and is agnostic towards machine learning training frameworks, offering at the same time wide support for leveraging deep learning accelerators such as embedded GPUs.
Proceedings ArticleDOI
ScriptPainter: Vision-based, On-device Test Script Generation for Mobile Systems
TL;DR: ScriptPainter is proposed, an easy-to-use automatic test script generator that enables a mobile phone to self-convert vision information on its screen into a test program; developers simply record a video while drawing a test scenario on a mobile touchscreen and ScriptPainter detects and tracks cursor locations in the video for generating a proper script.
Proceedings ArticleDOI
CrAM: A Compression-Aware Minimizer
TL;DR: A new compression-aware minimizer dubbed CrAM is proposed, which modifies the SGD training iteration in a principled way, in order to produce models whose local loss behavior is stable under compression operations such as weight pruning or quantization.
References
More filters
Posted Content
Rethinking the Inception Architecture for Computer Vision
TL;DR: This work is exploring ways to scale up networks in ways that aim at utilizing the added computation as efficiently as possible by suitably factorized convolutions and aggressive regularization.
Posted Content
MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications
Andrew Howard,Menglong Zhu,Bo Chen,Dmitry Kalenichenko,Weijun Wang,Tobias Weyand,M. Andreetto,Hartwig Adam +7 more
TL;DR: This work introduces two simple global hyper-parameters that efficiently trade off between latency and accuracy and demonstrates the effectiveness of MobileNets across a wide range of applications and use cases including object detection, finegrain classification, face attributes and large scale geo-localization.
Proceedings Article
Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Coding
TL;DR: Deep Compression as mentioned in this paper proposes a three-stage pipeline: pruning, quantization, and Huffman coding to reduce the storage requirement of neural networks by 35x to 49x without affecting their accuracy.
Posted Content
Google's Neural Machine Translation System: Bridging the Gap between Human and Machine Translation
Yonghui Wu,Mike Schuster,Zhifeng Chen,Quoc V. Le,Mohammad Norouzi,Wolfgang Macherey,Maxim Krikun,Yuan Cao,Qin Gao,Klaus Macherey,Jeff Klingner,Apurva Shah,Melvin Johnson,Xiaobing Liu,Łukasz Kaiser,Stephan Gouws,Yoshikiyo Kato,Taku Kudo,Hideto Kazawa,Keith Stevens,George Kurian,Nishant Patil,Wei Wang,Cliff Young,Jason A. Smith,Jason Riesa,Alex Rudnick,Oriol Vinyals,Greg S. Corrado,Macduff Hughes,Jeffrey Dean +30 more
TL;DR: GNMT, Google's Neural Machine Translation system, is presented, which attempts to address many of the weaknesses of conventional phrase-based translation systems and provides a good balance between the flexibility of "character"-delimited models and the efficiency of "word"-delicited models.
Proceedings Article
Learning both weights and connections for efficient neural networks
TL;DR: In this paper, the authors proposed a method to reduce the storage and computation required by neural networks by an order of magnitude without affecting their accuracy by learning only the important connections using a three-step method.