DUCKQUANT / THE QUANT & AI DIRECTORY
14,444 resources, ranked by in-directory PageRank
Showing 4,789–4,824 of 14,444 resources
Publication: Joint Neural Architecture Search and Quantization. Published Nov 23, 2018.
Publication: UNIQ: Uniform Noise Injection for Non-Uniform Quantization of Neural Networks. Published Apr 29, 2018.
Publication: Simultaneously Optimizing Weight and Quantizer of Ternary Neural Network using Truncated Gaussian Approximation. Published Oct 2, 2018.
Publication: Quantization for Rapid Deployment of Deep Neural Networks. Published Oct 12, 2018.
Publication: Quantizing deep convolutional networks for efficient inference: A whitepaper. Published Jun 21, 2018.
Publication: Rethinking floating point for deep learning. Published Nov 1, 2018.
Publication: On Periodic Functions as Regularizers for Quantization of Neural Networks. Published Nov 24, 2018.
Publication: Discovering Low-Precision Networks Close to Full-Precision Networks for Efficient Embedded Inference. Published Sep 11, 2018.
Publication: Quantizing Convolutional Neural Networks for Low-Power High-Throughput Inference Engines. Published May 21, 2018.
Publication: A Survey on Methods and Theories of Quantized Neural Networks. Published Aug 13, 2018.
Publication: Blended Coarse Gradient Descent for Full Quantization of Deep Neural Networks. Published Aug 15, 2018.
Publication: Learning Sparse Low-Precision Neural Networks With Learnable Regularization. Published Sep 1, 2018.
Publication: BinaryRelax: A Relaxation Approach For Training Deep Neural Networks With Quantized Weights. Published Jan 19, 2018.
Publication: LightNN: Filling the Gap between Conventional Deep Neural Networks and Binarized Networks. Published Dec 2, 2017.
Publication: ReBNet: Residual Binarized Neural Network. Published Nov 3, 2017.
Training Low-bits DNNs with Stochastic Quantization
Binary Convolution Network for faster real-time processing in ASICs
Publication: Overcoming Challenges in Fixed Point Training of Deep Convolutional Networks. Published Jul 8, 2016.
Publication: Ternary Neural Networks with Fine-Grained Quantization. Published May 2, 2017.
Publication: ShiftCNN: Generalized Low-Precision Architecture for Inference of Convolutional Neural Networks. Published Jun 7, 2017.
Publication: Soft-to-Hard Vector Quantization for End-to-End Learning Compressible Representations. Published Apr 3, 2017.
Publication: GXNOR-Net: Training deep neural networks with ternary weights and activations without full-precision memory under a unified discretization framework. Published May 25, 2017.
Publication: Balanced Quantization: An Effective and Efficient Approach to Quantized Neural Networks. Published Jun 22, 2017.
Publication: BMXNet: An Open-Source Binary Neural Network Implementation Based on MXNet. Published May 27, 2017.
Publication: FINN: A Framework for Fast, Scalable Binarized Neural Network Inference. Published Dec 1, 2016.
Publication: Soft Weight-Sharing for Neural Network Compression. Published Feb 13, 2017.
Publication: Incremental Network Quantization: Towards Lossless CNNs with Low-Precision Weights. Published Feb 10, 2017.
Publication: A GPU-Outperforming FPGA Accelerator Architecture for Binary Convolutional Neural Networks. Published Feb 20, 2017.
Publication: Local Binary Convolutional Neural Networks. Published Aug 22, 2016.
Publication: Ternary Neural Networks for Resource-Efficient AI Applications. Published Sep 1, 2016.
Publication: Performance Guaranteed Network Acceleration via High-Order Residual Quantization. Published Aug 29, 2017.
A script to convert floating-point CNN models into generalized low-precision ShiftCNN representation
Implementation of ICLR 2017 paper "Loss-aware Binarization of Deep Networks"
Caffe Implementation for Incremental network quantization
This code implements a demo of the Binarized Convolutional Landmark Localizers for Human Pose Estimation and Face Alignment with Limited Resources paper by Adrian…
