Hopfield networks is all you need

H Ramsauer, B Schäfl, J Lehner, P Seidl… - arxiv preprint arxiv …, 2020‏ - arxiv.org
We introduce a modern Hopfield network with continuous states and a corresponding
update rule. The new Hopfield network can store exponentially (with the dimension of the …

Arcface: Additive angular margin loss for deep face recognition

J Deng, J Guo, N Xue… - Proceedings of the IEEE …, 2019‏ - openaccess.thecvf.com
One of the main challenges in feature learning using Deep Convolutional Neural Networks
(DCNNs) for large-scale face recognition is the design of appropriate loss functions that can …

On sparse modern hopfield model

JYC Hu, D Yang, D Wu, C Xu… - Advances in Neural …, 2023‏ - 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 …

[ספר][B] Discrete energy on rectifiable sets

SV Borodachov, DP Hardin, EB Saff - 2019‏ - Springer
Our goal is to provide an introduction to the study of minimal energy problems, particularly
from the perspective of generating point configurations that provide useful discretizations of …

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 …

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 …

Efficient spherical designs with good geometric properties

RS Womersley - … computational mathematics-A celebration of the 80th …, 2018‏ - Springer
Spherical t-designs on 𝕊 d⊂ ℝ d+ 1 S^ d ⊂ R^ d+ 1 provide N nodes for an equal weight
numerical integration rule which is exact for all spherical polynomials of degree at most t …

A Comparison of Popular Point Configurations on

DP Hardin, TJ Michaels, EB Saff - arxiv preprint arxiv:1607.04590, 2016‏ - arxiv.org
There are many ways to generate a set of nodes on the sphere for use in a variety of
problems in numerical analysis. We present a survey of quickly generated point sets on …

Stationary representations: Optimally approximating compatibility and implications for improved model replacements

N Biondi, F Pernici, S Ricci… - Proceedings of the …, 2024‏ - openaccess.thecvf.com
Learning compatible representations enables the interchangeable use of semantic features
as models are updated over time. This is particularly relevant in search and retrieval systems …

Sparse and structured hopfield networks

S Santos, V Niculae, D McNamee… - arxiv preprint arxiv …, 2024‏ - arxiv.org
Modern Hopfield networks have enjoyed recent interest due to their connection to attention
in transformers. Our paper provides a unified framework for sparse Hopfield networks by …