中文
相关论文

相关论文: Capacity-resolution trade-off in the optimal learn…

200 篇论文

The storage of continuous variables in working memory is hypothesized to be sustained in the brain by the dynamics of recurrent neural networks (RNNs) whose steady states form continuous manifolds. In some cases, it is thought that the…

神经元与认知 · 定量生物学 2023-10-31 Haggai Agmon , Yoram Burak

Increasing the capacity of recurrent neural networks (RNN) usually involves augmenting the size of the hidden layer, with significant increase of computational cost. Recurrent neural tensor networks (RNTN) increase capacity using distinct…

计算与语言 · 计算机科学 2018-05-15 Alexandre Salle , Aline Villavicencio

Recurrent neural networks (RNNs) have proved effective at one dimensional sequence learning tasks, such as speech and online handwriting recognition. Some of the properties that make RNNs suitable for such tasks, for example robustness to…

人工智能 · 计算机科学 2007-05-23 Alex Graves , Santiago Fernandez , Juergen Schmidhuber

Neural systems are well known for their ability to learn and store information as memories. Even more impressive is their ability to abstract these memories to create complex internal representations, enabling advanced functions such as the…

神经与进化计算 · 计算机科学 2024-09-20 Lindsay M. Smith , Jason Z. Kim , Zhixin Lu , Dani S. Bassett

We study the learning dynamics and the representations emerging in Recurrent Neural Networks trained to integrate one or multiple temporal signals. Combining analytical and numerical investigations, we characterize the conditions under…

机器学习 · 计算机科学 2020-11-23 Arnaud Fanthomme , Rémi Monasson

Recurrent neural networks (RNN) are simple dynamical systems whose computational power has been attributed to their short-term memory. Short-term memory of RNNs has been previously studied analytically only for the case of orthogonal…

神经与进化计算 · 计算机科学 2016-04-26 Alireza Goudarzi , Sarah Marzen , Peter Banda , Guy Feldman , Christof Teuscher , Darko Stefanovic

Recurrent Neural Networks (RNNs) have found widespread applications in machine learning for time series prediction and dynamical systems reconstruction, and experienced a recent renaissance with improved training algorithms and…

机器学习 · 计算机科学 2026-04-14 Lukas Eisenmann , Alena Brändle , Zahra Monfared , Daniel Durstewitz

Despite the widespread application of recurrent neural networks (RNNs) across a variety of tasks, a unified understanding of how RNNs solve these tasks remains elusive. In particular, it is unclear what dynamical patterns arise in trained…

机器学习 · 计算机科学 2022-06-06 Kyle Aitken , Vinay V. Ramasesh , Ankush Garg , Yuan Cao , David Sussillo , Niru Maheswaranathan

Recurrent neural network (RNN) based reinforcement learning (RL) is used for learning context-dependent tasks and has also attracted attention as a method with remarkable learning performance in recent research. However, RNN-based RL has…

机器学习 · 计算机科学 2022-03-04 Toshitaka Matsuki

Convolutional neural network (CNN) is widely used in computer vision applications. In the networks that deal with images, CNNs are the most time-consuming layer of the networks. Usually, the solution to address the computation cost is to…

计算机视觉与模式识别 · 计算机科学 2019-11-26 Meisam Rakhshanfar

Reservoir computing is a powerful framework for real-time information processing, characterized by its high computational ability and quick learning, with applications ranging from machine learning to biological systems. In this paper, we…

无序系统与神经网络 · 物理学 2025-10-24 Shotaro Takasu , Toshio Aoyagi

Continuous attractor networks (CANs) are widely used to model how the brain temporarily retains continuous behavioural variables via persistent recurrent activity, such as an animal's position in an environment. However, this memory…

神经与进化计算 · 计算机科学 2025-07-02 Madison Cotteret , Christopher J. Kymn , Hugh Greatorex , Martin Ziegler , Elisabetta Chicca , Friedrich T. Sommer

Recurrent Neural Networks (RNNs) are a class of machine learning algorithms used for applications with time-series and sequential data. Recently, there has been a strong interest in executing RNNs on embedded devices. However, difficulties…

神经与进化计算 · 计算机科学 2020-03-23 Nesma M. Rezk , Madhura Purnaprajna , Tomas Nordström , Zain Ul-Abdin

Two potential bottlenecks on the expressiveness of recurrent neural networks (RNNs) are their ability to store information about the task in their parameters, and to store information about the input history in their units. We show…

机器学习 · 统计学 2017-03-06 Jasmine Collins , Jascha Sohl-Dickstein , David Sussillo

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

Convolutional neural network (CNN) and recurrent neural network (RNN) are two popular architectures used in text classification. Traditional methods to combine the strengths of the two networks rely on streamlining them or concatenating…

计算与语言 · 计算机科学 2020-06-30 Shengfei Lyu , Jiaqi Liu

We investigate the effect of the dimensionality of the representations learned in Deep Neural Networks (DNNs) on their robustness to input perturbations, both adversarial and random. To achieve low dimensionality of learned representations,…

机器学习 · 计算机科学 2020-02-20 Amartya Sanyal , Varun Kanade , Philip H. S. Torr , Puneet K. Dokania

We introduce a novel class of untrained Recurrent Neural Networks (RNNs) within the Reservoir Computing (RC) paradigm, called Residual Reservoir Memory Networks (ResRMNs). ResRMN combines a linear memory reservoir with a non-linear…

机器学习 · 计算机科学 2026-02-02 Matteo Pinna , Andrea Ceni , Claudio Gallicchio

In the last decade, Convolutional Neural Network with a multi-layer architecture has advanced rapidly. However, training its complex network is very space-consuming, since a lot of intermediate data are preserved across layers, especially…

分布式、并行与集群计算 · 计算机科学 2024-01-23 Zhigang Wang , Hangyu Yang , Ning Wang , Chuanfei Xu , Jie Nie , Zhiqiang Wei , Yu Gu , Ge Yu

Recurrent neural networks (RNNs) are powerful architectures to model sequential data, due to their capability to learn short and long-term dependencies between the basic elements of a sequence. Nonetheless, popular tasks such as speech or…

‹ 上一页 1 2 3 10 下一页 ›