English
Related papers

Related papers: Learning, Generalization, and Functional Entropy i…

200 papers

We systematically study and compare damage spreading for random Boolean and threshold networks under small external perturbations (damage), a problem which is relevant to many biological networks. We identify a new characteristic…

Disordered Systems and Neural Networks · Physics 2008-04-30 Thimo Rohlf , Natali Gulbahce , Christof Teuscher

Recently, graph neural networks (GNNs) have proved to be suitable in tasks on unstructured data. Particularly in tasks as community detection, node classification, and link prediction. However, most GNN models still operate with static…

Machine Learning · Computer Science 2019-06-07 Darwin Saire Pilco , Adín Ramírez Rivera

We evolve network topology of an asymmetrically connected threshold network by a simple local rewiring rule: quiet nodes grow links, active nodes lose links. This leads to convergence of the average connectivity of the network towards the…

Disordered Systems and Neural Networks · Physics 2009-10-31 Stefan Bornholdt , Thimo Rohlf

Deep reinforcement-learning methods have achieved remarkable performance on challenging control tasks. Observations of the resulting behavior give the impression that the agent has constructed a generalized representation that supports…

Machine Learning · Computer Science 2018-12-12 Sam Witty , Jun Ki Lee , Emma Tosch , Akanksha Atrey , Michael Littman , David Jensen

In this paper we propose a Bayesian method for estimating architectural parameters of neural networks, namely layer size and network depth. We do this by learning concrete distributions over these parameters. Our results show that regular…

Machine Learning · Statistics 2019-01-29 Georgi Dikov , Patrick van der Smagt , Justin Bayer

Neural networks readily learn a subset of the modular arithmetic tasks, while failing to generalize on the rest. This limitation remains unmoved by the choice of architecture and training strategies. On the other hand, an analytical…

Machine Learning · Computer Science 2024-06-06 Darshil Doshi , Tianyu He , Aritra Das , Andrey Gromov

We introduce a numerical method to study random Boolean networks with asynchronous stochas- tic update. Each node in the network of states starts with equal occupation probability and this probability distribution then evolves to a steady…

Statistical Mechanics · Physics 2015-05-18 Amer Shreim , Andrew Berdahl , Florian Greil , Jörn Davidsen , Maya Paczuski

Canalization is a classic concept in Developmental Biology that is thought to be an important feature of evolving systems. In a Boolean network it is a form of network robustness in which a subset of the input signals control the behavior…

Molecular Networks · Quantitative Biology 2015-05-28 Matthew D. Reichl , Kevin E. Bassler

An algorithm that learns from a set of examples should ideally be able to exploit the available resources of (a) abundant computing power and (b) domain-specific knowledge to improve its ability to generalize. Connectionist…

Artificial Intelligence · Computer Science 2008-02-03 D. W. Opitz , J. W. Shavlik

For Bayesian optimization (BO) on high-dimensional data with complex structure, neural network-based kernels for Gaussian processes (GPs) have been used to learn flexible surrogate functions by the high representation power of deep…

Machine Learning · Statistics 2021-11-02 Tomoharu Iwata

Background. A main theoretical puzzle is why over-parameterized Neural Networks (NNs) generalize well when trained to zero loss (i.e., so they interpolate the data). Usually, the NN is trained with Stochastic Gradient Descent (SGD) or one…

Machine Learning · Computer Science 2025-02-18 Gon Buzaglo , Itamar Harel , Mor Shpigel Nacson , Alon Brutzkus , Nathan Srebro , Daniel Soudry

We study the relationship between the frequency of a function and the speed at which a neural network learns it. We build on recent results that show that the dynamics of overparameterized neural networks trained with gradient descent can…

Machine Learning · Computer Science 2019-12-03 Ronen Basri , David Jacobs , Yoni Kasten , Shira Kritchman

Biological neural networks are shaped both by evolution across generations and by individual learning within an organism's lifetime, whereas standard artificial neural networks undergo a single, large training procedure without inherited…

Machine Learning · Computer Science 2025-05-01 Klemen Kotar , Greta Tuckute

The distributional simplicity bias (DSB) posits that neural networks learn low-order moments of the data distribution first, before moving on to higher-order correlations. In this work, we present compelling new evidence for the DSB by…

Machine Learning · Computer Science 2024-10-10 Nora Belrose , Quintin Pope , Lucia Quirke , Alex Mallen , Xiaoli Fern

The success of deep convolutional neural network (CNN) in computer vision especially image classification problems requests a new information theory for function of image, instead of image itself. In this article, after establishing a deep…

Machine Learning · Computer Science 2017-10-17 Ya-Hui Zhang

Graph neural networks (GNNs) have emerged as a fundamental tool for learning from graph-structured data, achieving strong performance across a wide range of applications. However, understanding their generalization capabilities remains…

Machine Learning · Computer Science 2026-05-14 Peiyao Wang , Liang Bai , Xian Yang , Richard Yi Da Xu , Jiye Liang

Overparameterized deep networks that generalize well have been key to the dramatic success of deep learning in recent years. The reasons for their remarkable ability to generalize are not well understood yet. When class labels in the…

Machine Learning · Computer Science 2026-02-03 Simran Ketha , Venkatakrishnan Ramaswamy

Graph neural networks (GNNs) are one of the most popular approaches to using deep learning on graph-structured data, and they have shown state-of-the-art performances on a variety of tasks. However, according to a recent study, a careful…

Machine Learning · Computer Science 2021-10-08 Jihoon Ko , Taehyung Kwon , Kijung Shin , Juho Lee

As a hybrid of artificial intelligence and quantum computing, quantum neural networks (QNNs) have gained significant attention as a promising application on near-term, noisy intermediate-scale quantum (NISQ) devices. Conventional QNNs are…

Quantum Physics · Physics 2024-04-09 Yadong Wu , Juan Yao , Pengfei Zhang , Xiaopeng Li

Dynamical systems theory and complexity science provide powerful tools for analysing artificial agents and robots. Furthermore, they have been recently proposed also as a source of design principles and guidelines. Boolean networks are a…

Artificial Intelligence · Computer Science 2015-03-18 Andrea Roli , Mattia Manfroni , Carlo Pinciroli , Mauro Birattari