English
Related papers

Related papers: Memory Capacity of a Random Neural Network

200 papers

Typical address-oriented computer memories cannot recognize incomplete or noisy information. Associative (content-addressable) memories solve this problem but suffer from severe capacity shortages. I propose a model of a quantum memory that…

Quantum Physics · Physics 2009-11-06 Carlo A. Trugenberger

This work has its origin in intuitive physical and statistical considerations. The problem of optimizing an artificial neural network is treated as a physical system, composed of a conservative vector force field. The derived scalar…

Machine Learning · Computer Science 2020-02-04 Francisco Yepes Barrera

The memorization capacity of neural networks with a given architecture has been thoroughly studied in many works. Specifically, it is well-known that memorizing $N$ samples can be done using a network of constant width, independent of $N$.…

Machine Learning · Computer Science 2025-02-18 Amitsour Egosi , Gilad Yehudai , Ohad Shamir

Empirical studies have widely demonstrated that neural networks are highly sensitive to small, adversarial perturbations of the input. The worst-case robustness against these so-called adversarial examples can be quantified by the Lipschitz…

Machine Learning · Statistics 2025-07-03 Paul Geuchen , Dominik Stöger , Thomas Telaar , Felix Voigtlaender

We analyze the expressivity of a universal deep neural network that can be organized as a series of nested qubit rotations, accomplished by adjustable data re-uploads. While the maximal expressive power increases with the depth of the…

Quantum Physics · Physics 2023-11-13 Iván Panadero , Yue Ban , Hilario Espinós , Ricardo Puebla , Jorge Casanova , Erik Torrontegui

Rational and neural network based approximations are efficient tools in modern approximation. These approaches are able to produce accurate approximations to nonsmooth and non-Lipschitz functions, including multivariate domain functions. In…

Optimization and Control · Mathematics 2023-09-08 Vinesha Peiris , Reinier Diaz Millan , Nadezda Sukhorukova , Julien Ugon

While the deployment of neural networks, yielding impressive results, becomes more prevalent in various applications, their interpretability and understanding remain a critical challenge. Network inversion, a technique that aims to…

Machine Learning · Computer Science 2024-02-20 Pirzada Suhail , Supratik Chakraborty , Amit Sethi

Numerical evaluations of the memory capacity (MC) of recurrent neural networks reported in the literature often contradict well-established theoretical bounds. In this paper, we study the case of linear echo state networks, for which the…

Machine Learning · Computer Science 2024-09-11 Giovanni Ballarin , Lyudmila Grigoryeva , Juan-Pablo Ortega

Neural networks can be compressed to reduce memory and computational requirements, or to increase accuracy by facilitating the use of a larger base architecture. In this paper we focus on pruning individual neurons, which can simultaneously…

Computer Vision and Pattern Recognition · Computer Science 2018-04-20 Bin Dai , Chen Zhu , David Wipf

We derive the calculation of two critical numbers predicting the behavior of perceptron networks. First, we derive the calculation of what we call the lossless memory (LM) dimension. The LM dimension is a generalization of the…

Neural and Evolutionary Computing · Computer Science 2018-09-11 Gerald Friedland , Mario Krell

Wireless information-centric networks consider storage as one of the network primitives, and propose to cache data within the network in order to improve latency and reduce bandwidth consumption. We study the throughput capacity and latency…

Networking and Internet Architecture · Computer Science 2016-11-17 Bita Azimdoost , Cedric Westphal , Hamid R. Sadjadpour

We study the ability of linear recurrent networks obeying discrete time dynamics to store long temporal sequences that are retrievable from the instantaneous state of the network. We calculate this temporal memory capacity for both…

Disordered Systems and Neural Networks · Physics 2009-11-10 Olivia L. White , Daniel D. Lee , Haim Sompolinsky

The spectra of random feature matrices provide essential information on the conditioning of the linear system used in random feature regression problems and are thus connected to the consistency and generalization of random feature models.…

Machine Learning · Statistics 2022-12-13 Zhijun Chen , Hayden Schaeffer , Rachel Ward

In this paper, we present a new technique to obtain upper bounds on undirected unicast network information capacity. Using this technique, we characterize an upper bound, called partition bound, on the symmetric rate of information flow in…

Information Theory · Computer Science 2020-10-27 Satyajit Thakor , Mohammad Ishtiyaq Qureshi

In this paper, a lower bound on the capacity of wireless ad hoc erasure networks is derived in closed form in the canonical case where $n$ nodes are uniformly and independently distributed in the unit area square. The bound holds almost…

Information Theory · Computer Science 2009-01-15 Rayyan G. Jaber , Jeffrey G. Andrews

The capacity of a channel can usually be characterized as a maximization of certain entropic quantities. From a practical point of view it is of primary interest to not only compute the capacity value, but also to find the corresponding…

Information Theory · Computer Science 2023-05-25 Holger Boche , Rafael F. Schaefer , H. Vincent Poor

Graph Neural Networks (GNNs) have achieved remarkable success across diverse tasks on graph-structured data, primarily through the use of learned weights in message passing layers. In this paper, we demonstrate that random weights can be…

Machine Learning · Computer Science 2025-02-04 Thu Bui , Carola-Bibiane Schönlieb , Bruno Ribeiro , Beatrice Bevilacqua , Moshe Eliasof

Random coding arguments are the backbone of most channel capacity achievability proofs. In this paper, we show that in their standard form, such arguments are insufficient for proving some network capacity theorems: structured coding…

Information Theory · Computer Science 2008-02-05 Bobak Nazer , Michael Gastpar

Reason and inference require process as well as memory skills by humans. Neural networks are able to process tasks like image recognition (better than humans) but in memory aspects are still limited (by attention mechanism, size). Recurrent…

Machine Learning · Computer Science 2017-03-03 Amit Sahu

Deep neural networks are highly expressive models that have recently achieved state of the art performance on speech and visual recognition tasks. While their expressiveness is the reason they succeed, it also causes them to learn…

Computer Vision and Pattern Recognition · Computer Science 2014-02-20 Christian Szegedy , Wojciech Zaremba , Ilya Sutskever , Joan Bruna , Dumitru Erhan , Ian Goodfellow , Rob Fergus