paper-with-me

홈 › Papers

Emergence of robust memory manifolds

2021-09-08 · Tankut Can, Kamesh Krishnamurthy

The ability to store continuous variables in the state of a biological system (e.g. a neural network) is critical for many behaviours. Most models for implementing such a memory manifold require hand-crafted symmetries in the interactions or precise fine-tuning of parameters. We present a general principle that we refer to as {\it frozen stabilisation} (FS), which allows a family of neural networks to self-organise to a critical state exhibiting multiple memory manifolds without parameter fine-tuning or symmetries. Memory manifolds arising from FS exhibit a wide range of emergent relaxational timescales and can be used as general purpose integrators for inputs aligned with the manifold. Moreover, FS allows robust memory manifolds in small networks, and this is relevant to debates of implementing continuous attractors with a small number of neurons in light of recent experimental discoveries.

📄 PDF Abstract BibTeX arXiv:2109.03879

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

OCTANE -- Optimal Control for Tensor-based Autoencoder Network Emergence: Explicit Case

2025-09-09 · Ratna Khatri, Anthony Kolshorn, Colin Olson, Harbir Antil arxiv

This paper presents a novel, mathematically rigorous framework for autoencoder-type deep neural networks that combines optimal control theory and low-rank tensor methods to yield memory-efficient training and automated a…

Image Denoising

Emergence of Separable Manifolds in Deep Language Representations

2020-06-01 · ICML 2020 1 · Jonathan Mamou, Hang Le, Miguel Del Rio, Cory Stephenson 외

Deep neural networks (DNNs) have shown much empirical success in solving perceptual tasks across various cognitive modalities. While they are only loosely inspired by the biological brain, recent studies report considera…

Generalizing Adam to Manifolds for Efficiently Training Transformers

2023-05-26 · Benedikt Brantner

One of the primary reasons behind the success of neural networks has been the emergence of an array of new, highly-successful optimizers, perhaps most importantly the Adam optimizer. It is widely used for training neural…

Physical Intuition

Memorization to Generalization: Emergence of Diffusion Models from Associative Memory

2025-05-27 · Bao Pham, Gabriel Raya, Matteo Negri, Mohammed J. Zaki 외

Hopfield networks are associative memory (AM) systems, designed for storing and retrieving patterns as local minima of an energy landscape. In the classical Hopfield model, an interesting phenomenon occurs when the amoun…

MemorizationRetrieval

On Dominant Manifolds in Reservoir Computing Networks

2026-04-07 · Noa Kaplan, Alberto Padoan, Anastasia Bizyaeva arxiv

Understanding how training shapes the geometry of recurrent network dynamics is a central problem in time-series modeling. We study the emergence of low-dimensional dominant manifolds in the training of Reservoir Computi…