On-device research index

arXiv research

A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.

169,181 papers · 148 categories

Trend · papers per month

count % of corpus

5 results for “hetero-associative”

Exponential Capacity in Multilayer Hetero-Associative Neural Networkscond-mat.dis-nn

Exponential neural networks store many patterns, mapping cues to targets.

problem Storing many patterns in a neural network efficiently and accurately.

method Introduced an exponential neural network with multiple layers, each storing a dataset.

result The network can store an exponential number of patterns, and it generalizes well to unseen data.

neural networks exponential capacity hetero-associative cavity analysis generalization

2026-07-31abs ↗pdf ↗

Beyond Disorder: Unveiling Cooperativeness in Multidirectional Associative Memoriescond-mat.dis-nn

New cooperative dynamics enhances retrieval performance in neural networks.

problem Understanding emergent computational capabilities in disordered systems.

method Leveraging statistical mechanics, extended neural network architecture for hetero-associative memory.

result Layers trained with less informative datasets develop retrieval regions of the same amplitude, leading to optimal performance.

neural networks statistical mechanics hetero-associative memory layer cooperativeness emergent phenomena

2025-03-06abs ↗pdf ↗

Supervised and Unsupervised protocols for hetero-associative neural networkscond-mat.dis-nn

Paper introduces supervised and unsupervised TAM models for binary neurons.

problem Learning and retrieval of structured triplets of patterns in neural networks.

method Extends Hebbian paradigm to supervised and unsupervised protocols, using glassy statistical mechanical techniques.

result Obtained self-consistency equations for critical dataset sizes and retrieval performance.

neural networks binary neurons structured triplets replica theory Hebbian synaptic couplings

2025-05-24abs ↗pdf ↗

Finite-size scaling of hetero-associative retrieval in continuous-signal-driven Ising spin systemscond-mat.dis-nn

A bridge between continuous signals and discrete Ising spins for associative memory.

problem Associative memory in continuous-signal-driven Ising spin systems.

method Multilayer Ising framework with PCA whitening and SimHash projection, coupled to pseudo-inverse memory couplings.

result Finite-size scaling of operational storage capacity with

α_c(N)=α_c(\infty)-c\,N^{-1/2}

, approaching

α_c(\infty)\approx 0.50

Ising spin systems Associative memory Finite-size scaling Continuous signals PCA whitening

2026-05-13abs ↗pdf ↗

Hebbian-Descentcs.LG

Proposes Hebbian-descent for neural network learning, addressing Hebbian and gradient descent issues.

problem Learning issues with correlated data and vanishing error term in gradient descent.

method Integrates Hebbian and gradient descent principles without activation function derivatives, centering neural activities.

result Biologically plausible, convergent, and effective in online learning with correlated data.

neural networks learning rules gradient descent Hebbian learning online learning

2019-05-25abs ↗pdf ↗