paper-with-me

Papers

Kernel Memory Networks: A Unifying Framework for Memory Modeling

2022-08-19 · Georgios Iatropoulos, Johanni Brea, Wulfram Gerstner

We consider the problem of training a neural network to store a set of patterns with maximal noise robustness. A solution, in terms of optimal weights and state update rules, is derived by training each individual neuron to perform either kernel classification or interpolation with a minimum weight norm. By applying this method to feed-forward and recurrent networks, we derive optimal models, termed kernel memory networks, that include, as special cases, many of the hetero- and auto-associative memory models that have been proposed over the past years, such as modern Hopfield networks and Kanerva's sparse distributed memory. We modify Kanerva's model and demonstrate a simple way to design a kernel memory network that can store an exponential number of continuous-valued patterns with a finite basin of attraction. The framework of kernel memory networks offers a simple and intuitive way to understand the storage capacity of previous memory models, and allows for new biological interpretations in terms of dendritic non-linearities and synaptic cross-talk.

📄 PDF Abstract BibTeX arXiv:2208.09416

Code (0)

등록된 구현이 없습니다.

Methods 이 논문이 사용한 방법론

Memory Network 설명 없음

Similar Papers 제목 키워드 기반

GPU-Fuzz: Finding Memory Errors in Deep Learning Frameworks

2026-02-11 · Zihao Li, Hongyi Lu, Yanan Guo, Zhenkai Zhang 외 arxiv

GPU memory errors are a critical threat to deep learning (DL) frameworks, leading to crashes or even security issues. We introduce GPU-Fuzz, a fuzzer locating these issues efficiently by modeling operator parameters as f…

Exponential Dynamic Energy Network for High Capacity Sequence Memory

2025-10-28 · Arjun Karuvally, Pichsinee Lertsaroj, Terrence J. Sejnowski, Hava T. Siegelmann arxiv

The energy paradigm, exemplified by Hopfield networks, offers a principled framework for memory in neural systems by interpreting dynamics as descent on an energy surface. While powerful for static associative memories, …

Nansde-net: A neural sde framework for generating time series with memory

2026-02-09 · Hiromu Ozai, Kei Nakagawa arxiv

Modeling time series with long- or short-memory characteristics is a fundamental challenge in many scientific and engineering domains. While fractional Brownian motion has been widely used as a noise source to capture su…

Scatterbrain: Unifying Sparse and Low-rank Attention Approximation

2021-10-28 · NeurIPS 2021 12 · Beidi Chen, Tri Dao, Eric Winsor, Zhao Song 외

Recent advances in efficient Transformers have exploited either the sparsity or low-rank properties of attention matrices to reduce the computational and memory bottlenecks of modeling long sequences. However, it is stil…

Image GenerationLanguage ModelingLanguage Modelling

Scatterbrain: Unifying Sparse and Low-rank Attention

2021-05-21 · NeurIPS 2021 12 · Beidi Chen, Tri Dao, Eric Winsor, Zhao Song 외

Recent advances in efficient Transformers have exploited either the sparsity or low-rank properties of attention matrices to reduce the computational and memory bottlenecks of modeling long sequences. However, it is stil…

Image GenerationLanguage ModelingLanguage Modelling