Hopfield Networks
PulseAugur coverage of Hopfield Networks — every cluster mentioning Hopfield Networks across labs, papers, and developer communities, ranked by signal.
3 day(s) with sentiment data
-
New AI framework generates synthetic patient data from small cohorts
Researchers have developed a new generative framework called Multiplicity-weighted Stochastic Attention (SA) that utilizes modern Hopfield networks to create synthetic patient data from small longitudinal cohorts. This …
-
New Hopfield Networks Achieve 10x Capacity Boost Using SU(d) Groups
Researchers have introduced generalized Hopfield networks that utilize continuous variables on Riemannian manifolds, specifically focusing on symmetric spaces associated with special unitary groups SU(d). This new appro…
-
New neural network architecture achieves exponential pattern storage
Researchers have developed a new multilayer hetero-associative neural network capable of storing an exponential number of patterns relative to its neurons. This network is designed for hetero-associative tasks, mapping …
-
Redundancy Maximization Boosts Hopfield Network Memory Capacity Tenfold
Researchers have introduced a novel approach to enhance the learning capabilities of Hopfield networks, a model traditionally used for associative memory. By applying principles from Partial Information Decomposition (P…
-
Energy-based transformers show promise in predicting reading difficulty
Researchers have introduced a new class of transformer models called energy-based transformers, which offer a formal connection to associative memory models. In computational psycholinguistics, this energy measure has b…
-
New Hopfield Network Variant Boosts Associative Memory Robustness
Researchers have introduced Convolutional Restricted Hopfield Networks (CRHNs) as a novel approach to associative memory, aiming to improve robustness against adversarial perturbations and input corruptions. Unlike exis…
-
Asymmetric Hopfield networks achieve superpolynomial sequence memory
Researchers have developed a novel construction for asymmetric Hopfield networks that significantly enhances their capacity for storing temporal sequences. These networks, utilizing binary neurons and synchronous update…
-
New ML framework unifies diverse methods, including Transformers
A new research paper introduces the "localization method," a general machine learning framework built on localization kernels and local means. This framework provides a unified theoretical foundation and demonstrates co…
-
Geometric entropy and phase transitions analyzed in continuous thermal dense associative memory
This paper explores the theoretical memory capacity of modern Hopfield networks, specifically Dense Associative Memory models with continuous states. It derives thermodynamic phase boundaries for these networks, compari…
-
Kernel Hopfield networks show high storage capacity, stability limits analyzed
Researchers have analyzed the geometric properties and storage capacity limits of kernel Hopfield networks trained with Kernel Logistic Regression (KLR). Their experiments, using random sequences and CIFAR-10 image embe…
-
New methods boost medical image segmentation with minimal annotations
Researchers have developed new semi-supervised learning techniques to improve image segmentation with significantly reduced annotation requirements. One method, SemiGDA, aligns feature and semantic distributions using d…