Open AccessPosted Content
XNOR-Net: ImageNet Classification Using Binary Convolutional Neural Networks
TLDR
XNOR-Nets as discussed by the authors approximate convolutions using primarily binary operations, which results in 58x faster convolutional operations and 32x memory savings, and outperforms BinaryConnect and BinaryNets by large margins on ImageNet.Abstract:
We propose two efficient approximations to standard convolutional neural networks: Binary-Weight-Networks and XNOR-Networks. In Binary-Weight-Networks, the filters are approximated with binary values resulting in 32x memory saving. In XNOR-Networks, both the filters and the input to convolutional layers are binary. XNOR-Networks approximate convolutions using primarily binary operations. This results in 58x faster convolutional operations and 32x memory savings. XNOR-Nets offer the possibility of running state-of-the-art networks on CPUs (rather than GPUs) in real-time. Our binary networks are simple, accurate, efficient, and work on challenging visual tasks. We evaluate our approach on the ImageNet classification task. The classification accuracy with a Binary-Weight-Network version of AlexNet is only 2.9% less than the full-precision AlexNet (in top-1 measure). We compare our method with recent network binarization methods, BinaryConnect and BinaryNets, and outperform these methods by large margins on ImageNet, more than 16% in top-1 accuracy.read more
Citations
More filters
Journal ArticleDOI
A 617-TOPS/W All-Digital Binary Neural Network Accelerator in 10-nm FinFET CMOS
Knag Phil,Gregory K. Chen,H. Ekin Sumbul,Raghavan Kumar,Steven K. Hsu,Amit Agarwal,Monodeep Kar,Seongjong Kim,Mark A. Anders,Himanshu Kaul,Ram Krishnamurthy +10 more
TL;DR: The bit-serial binary operation allows for bit-accurate operation and high DNN accuracy that multibit analog compute-in-memory designs struggle to attain and provides favorable energy tradeoffs compared with small-integer digital DNN accelerators.
Proceedings ArticleDOI
Minimum precision requirements for the SVM-SGD learning algorithm
TL;DR: Analytical lower bounds on the precision requirements for the commonly employed stochastic gradient descent on-line learning algorithm in the specific context of a support vector machine (SVM) are presented.
Journal ArticleDOI
Real-Time SSDLite Object Detection on FPGA
TL;DR: This article proposes an efficient computing system for real-time SSDLite object detection on FPGA devices, which includes novel hardware architecture and system optimization techniques.
Journal ArticleDOI
Big data in nanoscale connectomics, and the greed for training labels
TL;DR: The neurosciences have developed methods that outpace most other biomedical fields in terms of acquired bytes, but the information content and analysis challenge of such data indicates that electron microscopy (EM)-based connectomics is an especially hard problem.
Posted Content
Quantized Reinforcement Learning (QuaRL)
Srivatsan Krishnan,Sharad Chitlangia,Maximilian Lam,Zishen Wan,Aleksandra Faust,Vijay Janapa Reddi +5 more
TL;DR: This first comprehensive empirical study that quantifies the effects of quantization on various deep reinforcement learning policies with the intent to reduce their computational resource demands and demonstrates real-world applications ofquantization for reinforcement learning.
References
More filters
Proceedings ArticleDOI
Deep Residual Learning for Image Recognition
TL;DR: In this article, the authors proposed a residual learning framework to ease the training of networks that are substantially deeper than those used previously, which won the 1st place on the ILSVRC 2015 classification task.
Proceedings Article
Adam: A Method for Stochastic Optimization
Diederik P. Kingma,Jimmy Ba +1 more
TL;DR: This work introduces Adam, an algorithm for first-order gradient-based optimization of stochastic objective functions, based on adaptive estimates of lower-order moments, and provides a regret bound on the convergence rate that is comparable to the best known results under the online convex optimization framework.
Proceedings Article
ImageNet Classification with Deep Convolutional Neural Networks
TL;DR: The state-of-the-art performance of CNNs was achieved by Deep Convolutional Neural Networks (DCNNs) as discussed by the authors, which consists of five convolutional layers, some of which are followed by max-pooling layers, and three fully-connected layers with a final 1000-way softmax.
Proceedings Article
Very Deep Convolutional Networks for Large-Scale Image Recognition
Karen Simonyan,Andrew Zisserman +1 more
TL;DR: This work investigates the effect of the convolutional network depth on its accuracy in the large-scale image recognition setting using an architecture with very small convolution filters, which shows that a significant improvement on the prior-art configurations can be achieved by pushing the depth to 16-19 weight layers.
Proceedings Article
Very Deep Convolutional Networks for Large-Scale Image Recognition
Karen Simonyan,Andrew Zisserman +1 more
TL;DR: In this paper, the authors investigated the effect of the convolutional network depth on its accuracy in the large-scale image recognition setting and showed that a significant improvement on the prior-art configurations can be achieved by pushing the depth to 16-19 layers.