paper-with-me

홈 › Papers

How noise affects memory in linear recurrent networks

2024-09-05 · JingChuan Guan, Tomoyuki Kubota, Yasuo Kuniyoshi, Kohei Nakajima

The effects of noise on memory in a linear recurrent network are theoretically investigated. Memory is characterized by its ability to store previous inputs in its instantaneous state of network, which receives a correlated or uncorrelated noise. Two major properties are revealed: First, the memory reduced by noise is uniquely determined by the noise's power spectral density (PSD). Second, the memory will not decrease regardless of noise intensity if the PSD is in a certain class of distribution (including power law). The results are verified using the human brain signals, showing good agreement.

📄 PDF Abstract BibTeX arXiv:2409.03187

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Recurrent Dynamic Embedding for Video Object Segmentation

2022-05-08 · CVPR 2022 1 · Mingxing Li, Li Hu, Zhiwei Xiong, Bang Zhang 외

Space-time memory (STM) based video object segmentation (VOS) networks usually keep increasing memory bank every several frames, which shows excellent performance. However, 1) the hardware cannot withstand the ever-incre…

ObjectSemantic SegmentationSemi-Supervised Video Object SegmentationVideo Object Segmentation+1

Attend Locally, Remember Linearly: Linear Attention as Cross-Frame Memory for Autoregressive Video Diffusion

2026-05-15 · Kunyang Li, Mubarak Shah, Yuzhang Shang arxiv

Autoregressive (AR) video diffusion is a powerful paradigm for streaming and interactive video generation. However, its reliance on softmax self-attention leads to quadratic compute complexity in sequence length and memo…

Video Generation

A theory of sequence indexing and working memory in recurrent neural networks

2018-02-28 · E. Paxon Frady, Denis Kleyko, Friedrich T. Sommer

To accommodate structured approaches of neural computation, we propose a class of recurrent neural networks for indexing and storing sequences of symbols or analog data vectors. These networks with randomized input weigh…

Retrieval

Improved memory in recurrent neural networks with sequential non-normal dynamics

2019-05-31 · ICLR 2020 1 · A. Emin Orhan, Xaq Pitkow

Training recurrent neural networks (RNNs) is a hard problem due to degeneracies in the optimization landscape, a problem also known as vanishing/exploding gradients. Short of designing new RNN architectures, previous met…

Linear Memory Networks

2018-11-08 · Davide Bacciu, Antonio Carta, Alessandro Sperduti

Recurrent neural networks can learn complex transduction problems that require maintaining and actively exploiting a memory of their inputs. Such models traditionally consider memory and input-output functionalities indi…