中文
相关论文

相关论文: Neural Speed Reading via Skim-RNN

200 篇论文

Recurrent Neural Networks (RNNs) continue to show outstanding performance in sequence modeling tasks. However, training RNNs on long sequences often face challenges like slow inference, vanishing gradients and difficulty in capturing long…

人工智能 · 计算机科学 2018-02-06 Victor Campos , Brendan Jou , Xavier Giro-i-Nieto , Jordi Torres , Shih-Fu Chang

Recurrent neural networks (RNNs) can model natural language by sequentially 'reading' input tokens and outputting a distributed representation of each token. Due to the sequential nature of RNNs, inference time is linearly dependent on the…

计算与语言 · 计算机科学 2019-04-03 Christian Hansen , Casper Hansen , Stephen Alstrup , Jakob Grue Simonsen , Christina Lioma

Recurrent Neural Networks are showing much promise in many sub-areas of natural language processing, ranging from document classification to machine translation to automatic question answering. Despite their promise, many recurrent models…

计算与语言 · 计算机科学 2017-05-02 Adams Wei Yu , Hongrae Lee , Quoc V. Le

Recurrent neural networks have achieved great success in many NLP tasks. However, they have difficulty in parallelization because of the recurrent structure, so it takes much time to train RNNs. In this paper, we introduce sliced recurrent…

计算与语言 · 计算机科学 2018-07-09 Zeping Yu , Gongshen Liu

Deep neural network (DNN) based speech enhancement models have attracted extensive attention due to their promising performance. However, it is difficult to deploy a powerful DNN in real-time applications because of its high computational…

声音 · 计算机科学 2022-07-25 Xiaohuai Le , Tong Lei , Kai Chen , Jing Lu

Recurrent neural networks (RNNs) provide state-of-the-art performance in processing sequential data but are memory intensive to train, limiting the flexibility of RNN models which can be trained. Reversible RNNs---RNNs for which the…

机器学习 · 计算机科学 2018-10-26 Matthew MacKay , Paul Vicol , Jimmy Ba , Roger Grosse

Recurrent Neural Networks (RNNs) are powerful tools for solving sequence-based problems, but their efficacy and execution time are dependent on the size of the network. Following recent work in simplifying these networks with model pruning…

神经与进化计算 · 计算机科学 2018-04-30 Feiwen Zhu , Jeff Pool , Michael Andersch , Jeremy Appleyard , Fung Xie

We introduce MinimalRNN, a new recurrent neural network architecture that achieves comparable performance as the popular gated RNNs with a simplified structure. It employs minimal updates within RNN, which not only leads to efficient…

机器学习 · 统计学 2018-06-21 Minmin Chen

Scene text recognition has drawn great attentions in the community of computer vision and artificial intelligence due to its challenges and wide applications. State-of-the-art recurrent neural networks (RNN) based models map an input…

计算机视觉与模式识别 · 计算机科学 2018-06-05 Yi-Chao Wu , Fei Yin , Xu-Yao Zhang , Li Liu , Cheng-Lin Liu

Spiking Neural Networks (SNNs) have recently attracted widespread research interest as an efficient alternative to traditional Artificial Neural Networks (ANNs) because of their capability to process sparse and binary spike information and…

神经与进化计算 · 计算机科学 2023-05-30 Yuhang Li , Abhishek Moitra , Tamar Geller , Priyadarshini Panda

Deep neural network (DNN) based approaches hold significant potential for reinforcement learning (RL) and have already shown remarkable gains over state-of-art methods in a number of applications. The effectiveness of DNN methods can be…

机器学习 · 统计学 2017-06-01 Henghui Zhu , Feng Nan , Ioannis Paschalidis , Venkatesh Saligrama

Spiking neural networks (SNNs) have shown advantages in computation and energy efficiency over traditional artificial neural networks (ANNs) thanks to their event-driven representations. SNNs also replace weight multiplications in ANNs with…

神经与进化计算 · 计算机科学 2023-06-01 Yangfan Hu , Qian Zheng , Xudong Jiang , Gang Pan

Spike train classification has recently become an important topic in the machine learning community, where each spike train is a binary event sequence with \emph{temporal-sparsity of signals of interest} and \emph{temporal-noise}…

神经与进化计算 · 计算机科学 2024-11-12 Hang Yin , Yao Su , Liping Liu , Thomas Hartvigsen , Xin Dai , Xiangnan Kong

Spiking Neural Networks (SNNs) as Machine Learning (ML) models have recently received a lot of attention as a potentially more energy-efficient alternative to conventional Artificial Neural Networks. The non-differentiability and sparsity…

机器学习 · 计算机科学 2025-12-05 Maximilian Gollwitzer , Felix Dietrich

Spiking Neural Networks (SNN) are a class of bio-inspired neural networks that promise to bring low-power and low-latency inference to edge devices through asynchronous and sparse processing. However, being temporal models, SNNs depend…

计算机视觉与模式识别 · 计算机科学 2024-04-19 Asude Aydin , Mathias Gehrig , Daniel Gehrig , Davide Scaramuzza

Recurrent Neural Networks (RNNs) are a key technology for applications such as automatic speech recognition or machine translation. Unlike conventional feed-forward DNNs, RNNs remember past information to improve the accuracy of future…

神经与进化计算 · 计算机科学 2022-02-16 Franyell Silfa , Jose-Maria Arnau , Antonio González

Recurrent neural networks are a powerful tool for modeling sequential data, but the dependence of each timestep's computation on the previous timestep's output limits parallelism and makes RNNs unwieldy for very long sequences. We introduce…

神经与进化计算 · 计算机科学 2016-11-22 James Bradbury , Stephen Merity , Caiming Xiong , Richard Socher

Scene text image contains two levels of contents: visual texture and semantic information. Although the previous scene text recognition methods have made great progress over the past few years, the research on mining semantic information to…

计算机视觉与模式识别 · 计算机科学 2020-03-30 Deli Yu , Xuan Li , Chengquan Zhang , Junyu Han , Jingtuo Liu , Errui Ding

This paper presents a new methodology to alleviate the fundamental trade-off between accuracy and latency in spiking neural networks (SNNs). The approach involves decoding confidence information over time from the SNN outputs and using it…

计算机视觉与模式识别 · 计算机科学 2023-11-29 Chen Li , Edward Jones , Steve Furber

Many neural networks exhibit stability in their activation patterns over time in response to inputs from sensors operating under real-world conditions. By capitalizing on this property of natural signals, we propose a Recurrent Neural…

神经与进化计算 · 计算机科学 2016-12-19 Daniel Neil , Jun Haeng Lee , Tobi Delbruck , Shih-Chii Liu
‹ 上一页 1 2 3 10 下一页 ›