paper-with-me

Papers

Efficient Stochastic Inference of Bitwise Deep Neural Networks

2016-11-20 · Sebastian Vogel, Christoph Schorn, Andre Guntoro, Gerd Ascheid

Recently published methods enable training of bitwise neural networks which allow reduced representation of down to a single bit per weight. We present a method that exploits ensemble decisions based on multiple stochastically sampled network models to increase performance figures of bitwise neural networks in terms of classification accuracy at inference. Our experiments with the CIFAR-10 and GTSRB datasets show that the performance of such network ensembles surpasses the performance of the high-precision base model. With this technique we achieve 5.81% best classification error on CIFAR-10 test set using bitwise networks. Concerning inference on embedded systems we evaluate these bitwise networks using a hardware efficient stochastic rounding procedure. Our work contributes to efficient embedded bitwise neural networks.

📄 PDF Abstract BibTeX arXiv:1611.06539

Code (0)

등록된 구현이 없습니다.

Tasks

General Classification

Similar Papers 제목 키워드 기반

Dedicated Inference Engine and Binary-Weight Neural Networks for Lightweight Instance Segmentation

2025-01-03 · Tse-Wei Chen, Wei Tao, Dongyue Zhao, Kazuhiro Mima 외

Reducing computational costs is an important issue for development of embedded systems. Binary-weight Neural Networks (BNNs), in which weights are binarized and activations are quantized, are employed to reduce computati…

Instance SegmentationSemantic Segmentation

Stochastic CHAOS: Why Deterministic Inference Kills, and Distributional Variability Is the Heartbeat of Artifical Cognition

2026-01-12 · Tanmay Joshi, Shourya Aggarwal, Anusa Saha, Aadi Pandey 외 arxiv

Deterministic inference is a comforting ideal in classical software: the same program on the same input should always produce the same output. As large language models move into real-world deployment, this ideal has been…

DiverseAR: Boosting Diversity in Bitwise Autoregressive Image Generation

2025-12-02 · Ying Yang, Zhengyao Lv, Tianlin Pan, Haofan Wang 외 arxiv

In this paper, we investigate the underexplored challenge of sample diversity in autoregressive (AR) generative models with bitwise visual tokenizers. We first analyze the factors that limit diversity in bitwise AR model…

Binary ClassificationImage Generation

Hessian-aware Training for Enhancing DNNs Resilience to Parameter Corruptions

2025-04-02 · Tahmid Hasan Prato, Seijoon Kim, Lizhong Chen, Sanghyun Hong

Deep neural networks are not resilient to parameter corruptions: even a single-bitwise error in their parameters in memory can cause an accuracy drop of over 10%, and in the worst cases, up to 99%. This susceptibility po…

NP4G : Network Programming for Generalization

2022-12-08 · Shoichiro Hara, Yuji Watanabe

Automatic programming has been actively studied for a long time by various approaches including genetic programming. In recent years, automatic programming using neural networks such as GPT-3 has been actively studied an…