English
Related papers

Related papers: Optimal storage capacity of neural networks at fin…

200 papers

The inclusion of a threshold in the dynamics of layered neural networks with variable activity is studied at arbitrary temperature. In particular, the effects on the retrieval quality of a self-controlled threshold obtained by forcing the…

Disordered Systems and Neural Networks · Physics 2009-10-31 D. Bolle' , G. Massolo

The large variation of datasets is a huge barrier for image classification tasks. In this paper, we embraced this observation and introduce the finite temperature tensor network (FTTN), which imports the thermal perturbation into the matrix…

Machine Learning · Computer Science 2021-04-27 Haoxiang Lin , Shuqian Ye , Xi Zhu

Quantum neural networks form one pillar of the emergent field of quantum machine learning. Here, quantum generalisations of classical networks realizing associative memories - capable of retrieving patterns, or memories, from corrupted…

Quantum Physics · Physics 2025-03-28 Lukas Bödeker , Eliana Fiorelli , Markus Müller

In this work we study, analytically and employing Monte Carlo simulations, the influence of the competition between several activity-dependent synaptic processes, such as short-term synaptic facilitation and depression, on the maximum…

Neurons and Cognition · Quantitative Biology 2010-07-23 Jorge F. Mejias , Joaquin J. Torres

The storage capacity of a binary classification model is the maximum number of random input-output pairs per parameter that the model can learn. It is one of the indicators of the expressive power of machine learning models and is important…

Disordered Systems and Neural Networks · Physics 2024-12-02 Sota Nishiyama , Masayuki Ohzeki

The performance of large neural networks can be judged not only by their storage capacity but also by the time required for learning. A polynomial learning algorithm with learning time $\sim N^2$ in a network with $N$ units might be…

Disordered Systems and Neural Networks · Physics 2017-02-08 Heinz Horner , Anthea Bethge

We studied the computational properties of an attractor neural network (ANN) with different network topologies. Though fully connected neural networks exhibit, in general, a good performance, they are biologically unrealistic, as it is…

Statistical Mechanics · Physics 2007-05-23 Joaquin J. Torres , Miguel A. Munoz , J. Marro , P. L. Garrido

The heat capacity $\mathcal{C}$ of a given probe is a fundamental quantity that determines, among other properties, the maximum precision in temperature estimation. In turn, $\mathcal{C}$ is limited by a quadratic scaling with the number of…

Synaptic efficacy between neurons is known to change within a short time scale dynamically. Neurophysiological experiments show that high-frequency presynaptic inputs decrease synaptic efficacy between neurons. This phenomenon is called…

Disordered Systems and Neural Networks · Physics 2015-05-28 Yosuke Otsubo , Kenji Nagata , Masafumi Oizumi , Masato Okada

We use a formal correspondence between thermodynamics and inference, where the number of samples can be thought of as the inverse temperature, to study a quantity called ``learning capacity'' which is a measure of the effective…

Machine Learning · Computer Science 2024-10-22 Daiwei Chen , Wei-Kai Chang , Pratik Chaudhari

We calculate the dependence of heat capacity of a free standing thin membrane on its thickness and temperature. A remarkable fact is that for a given temperature there exists a minimum in the dependence of the heat capacity on the…

Other Condensed Matter · Physics 2009-11-11 O. V. Fefelov , J Bergli , Y M Galperin

This paper considers the problem of information capacity of a random neural network. The network is represented by matrices that are square and symmetrical. The matrices have a weight which determines the highest and lowest possible value…

Neural and Evolutionary Computing · Computer Science 2012-11-16 Matt Stowe

We study a refrigerator model which consists of two $n$-level systems interacting via a pulsed external field. Each system couples to its own thermal bath at temperatures $T_h$ and $T_c$, respectively ($\theta\equiv T_c/T_h<1$). The…

Statistical Mechanics · Physics 2009-06-16 Armen E. Allahverdyan , Karen Hovhannisyan , Guenter Mahler

We estimate the critical capacity of the zero-temperature Hopfield model by using a novel and rigorous method. The probability of having a stable fixed point is one when $\alpha\le 0.113$ for a large number of neurons. This result is an…

Mathematical Physics · Physics 2009-10-31 J. Feng , M. Shcherbina , B. Tirozzi

We present a simple model that recalls two different patterns depending on the temperature. To realize a change in recall pattern due to temperature change, we embed two patterns to different graphs: the first pattern into a fully connected…

Disordered Systems and Neural Networks · Physics 2026-02-25 Munetaka Sasaki

Deep neural networks (DNNs) depend on the storage of a large number of parameters, which consumes an important portion of the energy used during inference. This paper considers the case where the energy usage of memory elements can be…

Machine Learning · Computer Science 2019-12-24 Sébastien Henwood , François Leduc-Primeau , Yvon Savaria

Recent experimental and theoretical studies show that energy efficiency, which measures the amount of information processed by a neuron with per unit of energy consumption, plays an important role in the evolution of neural systems. Here,…

Biological Physics · Physics 2019-11-22 Long-Fei Wang , Fei Jia , Xiao-Zhi Liu , Ya-lei Song , Lian-Chun Yu

We present results for two different kinds of high order connections between neurons acting as corrections to the Hopfield model. Equilibrium properties are analyzed using the replica mean-field theory and compared with numerical…

Condensed Matter · Physics 2009-10-22 J. J. Arenzon , R. M. C. de Almeida

With the help of quantum mechanics one can formulate a model of associative memory with optimal storage capacity. I generalize this model by introducing a parameter playing the role of an effective temperature. The corresponding…

Quantum Physics · Physics 2009-11-07 Carlo A. Trugenberger

Fine-tuning large pre-trained models is a common practice in machine learning applications, yet its mathematical analysis remains largely unexplored. In this paper, we study fine-tuning through the lens of memorization capacity. Our new…

Machine Learning · Computer Science 2024-08-20 Jy-yong Sohn , Dohyun Kwon , Seoyeon An , Kangwook Lee
‹ Prev 1 2 3 10 Next ›