On sparse modern hopfield model

JYC Hu, D Yang, D Wu, C Xu… - Advances in Neural …, 2024 - proceedings.neurips.cc
We introduce the sparse modern Hopfield model as a sparse extension of the modern
Hopfield model. Like its dense counterpart, the sparse modern Hopfield model equips a …

STanhop: Sparse tandem hopfield model for memory-enhanced time series prediction

D Wu, JYC Hu, W Li, BY Chen, H Liu - arXiv preprint arXiv:2312.17346, 2023 - arxiv.org
We present STanHop-Net (Sparse Tandem Hopfield Network) for multivariate time series
prediction with memory-enhanced capabilities. At the heart of our approach is STanHop, a …

Provably optimal memory capacity for modern hopfield models: Transformer-compatible dense associative memories as spherical codes

JYC Hu, D Wu, H Liu - arXiv preprint arXiv:2410.23126, 2024 - arxiv.org
We study the optimal memorization capacity of modern Hopfield models and Kernelized
Hopfield Models (KHMs), a transformer-compatible class of Dense Associative Memories …

[HTML][HTML] The generative neural microdynamics of cognitive processing

DC McNamee - Current Opinion in Neurobiology, 2024 - Elsevier
The entorhinal cortex and hippocampus form a recurrent network that informs many
cognitive processes, including memory, planning, navigation, and imagination. Neural …

Nonparametric modern hopfield models

JYC Hu, BY Chen, D Wu, F Ruan, H Liu - arXiv preprint arXiv:2404.03900, 2024 - arxiv.org
We present a nonparametric construction for deep learning compatible modern Hopfield
models and utilize this framework to debut an efficient variant. Our key contribution stems …

Uniform memory retrieval with larger capacity for modern hopfield models

D Wu, JYC Hu, TY Hsiao, H Liu - arXiv preprint arXiv:2404.03827, 2024 - arxiv.org
We propose a two-stage memory retrieval dynamics for modern Hopfield models, termed
$\mathtt {U\text {-} Hop} $, with enhanced memory capacity. Our key contribution is a …

Modern Hopfield Networks meet Encoded Neural Representations--Addressing Practical Considerations

S Kashyap, NS D'Souza, L Shi, KCL Wong… - arXiv preprint arXiv …, 2024 - arxiv.org
Content-addressable memories such as Modern Hopfield Networks (MHN) have been
studied as mathematical models of auto-association and storage/retrieval in the human …

The Role of Recurrency in Image Segmentation for Noisy and Limited Sample Settings

D Calhas, J Marques, AL Oliveira - arXiv preprint arXiv:2412.15734, 2024 - arxiv.org
The biological brain has inspired multiple advances in machine learning. However, most
state-of-the-art models in computer vision do not operate like the human brain, simply …