English
Related papers

Related papers: Hebbian Inspecificity in the Oja Model

200 papers

Imagine a robot controller with the ability to adapt like human synapses, dynamically rewiring itself to overcome unforeseen challenges in real time. This paper proposes a novel zero-shot adaptation mechanism for evolutionary robotics,…

Robotics · Computer Science 2025-08-06 Hamze Hammami , Eva Denisa Barbulescu , Talal Shaikh , Mouayad Aldada , Muhammad Saad Munawar

Recent works have derived neural networks with online correlation-based learning rules to perform \textit{kernel similarity matching}. These works applied existing linear similarity matching algorithms to nonlinear features generated with…

Neural and Evolutionary Computing · Computer Science 2022-04-18 Kyle Luther , H. Sebastian Seung

In this paper we propose an algorithm, Simple Hebbian PCA, and prove that it is able to calculate the principal component analysis (PCA) in a distributed fashion across nodes. It simplifies existing network structures by removing intralayer…

Neural and Evolutionary Computing · Computer Science 2017-08-16 Leonard Johard , Victor Rivera , Manuel Mazzara , JooYoung Lee

We have recently shown that the statistical properties of goal directed reaching in human subjects depends on recent experience in a way that is consistent with the presence of adaptive Bayesian priors (Verstynen and Sabes, 2011). We also…

Disordered Systems and Neural Networks · Physics 2011-06-16 Timothy Verstynen , Philip N. Sabes

Previous analytical studies of on-line Independent Component Analysis (ICA) learning rules have focussed on asymptotic stability and efficiency. In practice the transient stages of learning will often be more significant in determining the…

Disordered Systems and Neural Networks · Physics 2007-05-23 Magnus Rattray

In this paper, training a neural network is identified, exactly, as a search through Hamilton--Jacobi initial-value problems: each gradient step selects the initial data of a viscous Hamilton--Jacobi equation whose Hopf--Cole propagator…

Machine Learning · Computer Science 2026-05-29 Jose Marie Antonio Miñoza , Erika Fille T. Legara , Christopher P. Monterola

Principal component analysis (PCA) aims at estimating the direction of maximal variability of a high-dimensional dataset. A natural question is: does this task become easier, and estimation more accurate, when we exploit additional…

Information Theory · Computer Science 2014-06-19 Andrea Montanari , Emile Richard

In high-dimensional principal component analysis, important inferential targets include both leading spikes and the associated principal eigenspaces. Such problems arise naturally in high-dimensional factor models, where leading principal…

Statistics Theory · Mathematics 2026-03-26 Yanqing Yin , Wang Zhou

We study attention mechanisms through the lens of a canonical unsupervised problem: principal component analysis (PCA). We show that, when trained on Gaussian data, both softmax and linear attention layers learn parameters that align with…

Optimization and Control · Mathematics 2026-05-19 Rodrigo Maulen-Soto , Claire Boyer

Attention-based regression models are often trained by jointly optimizing Mean Squared Error (MSE) loss and Pearson correlation coefficient (PCC) loss, emphasizing the magnitude of errors and the order or shape of targets, respectively. A…

Machine Learning · Computer Science 2026-02-23 Jingquan Yan , Yuwei Miao , Peiran Yu , Junzhou Huang

Gibbs-ERM learning is a natural idealized model of learning with stochastic optimization algorithms (such as Stochastic Gradient Langevin Dynamics and ---to some extent--- Stochastic Gradient Descent), while it also arises in other…

Machine Learning · Computer Science 2019-02-06 Ilja Kuzborskij , Nicolò Cesa-Bianchi , Csaba Szepesvári

Finding the optimal hyperparameters of a model can be cast as a bilevel optimization problem, typically solved using zero-order techniques. In this work we study first-order methods when the inner optimization problem is convex but…

Generating functionals may guide the evolution of a dynamical system and constitute a possible route for handling the complexity of neural networks as relevant for computational intelligence. We propose and explore a new objective function,…

Neurons and Cognition · Quantitative Biology 2017-11-27 Rodrigo Echeveste , Claudius Gros

This paper is concerned with the modeling and analysis of two of the most commonly used recurrent neural network models (i.e., Hopfield neural network and firing-rate neural network) with dynamic recurrent connections undergoing Hebbian…

Optimization and Control · Mathematics 2024-03-25 Veronica Centorrino , Francesco Bullo , Giovanni Russo

In neuroscience, classical Hopfield networks are the standard biologically plausible model of long-term memory, relying on Hebbian plasticity for storage and attractor dynamics for recall. In contrast, memory-augmented neural networks in…

Neurons and Cognition · Quantitative Biology 2021-10-28 Danil Tyulmankov , Ching Fang , Annapurna Vadaparty , Guangyu Robert Yang

We introduce a class of $M \times M$ sample covariance matrices $\mathcal Q$ which subsumes and generalizes several previous models. The associated population covariance matrix $\Sigma = \mathbb E \cal Q$ is assumed to differ from the…

Probability · Mathematics 2015-01-19 Alex Bloemendal , Antti Knowles , Horng-Tzer Yau , Jun Yin

In this work, we begin by questioning the existence of a new kind of nonergodic extended phase, namely, the many-body critical (MBC) phase in finite systems of an interacting quasiperiodic system. We find that this phase can be separately…

Disordered Systems and Neural Networks · Physics 2025-05-23 Aamna Ahmed , Nilanjan Roy

Learning features invariant to arbitrary transformations in the data is a requirement for any recognition system, biological or artificial. It is now widely accepted that simple cells in the primary visual cortex respond to features while…

Neural and Evolutionary Computing · Computer Science 2020-12-14 Jayanta K. Dutta , Bonny Banerjee

An important problem in machine learning is the ability to learn tasks in a sequential manner. If trained with standard first-order methods most models forget previously learned tasks when trained on a new task, which is often referred to…

Machine Learning · Statistics 2021-12-10 Reinhard Heckel

Many pattern recognition methods rely on statistical information from centered data, with the eigenanalysis of an empirical central moment, such as the covariance matrix in principal component analysis (PCA), as well as partial least…

Machine Learning · Statistics 2014-07-11 Paul Honeine