English
Related papers

Related papers: Nested canalyzing depth and network stability

200 papers

Graph neural networks (GNNs) have become increasingly popular for classification tasks on graph-structured data. Yet, the interplay between graph topology and feature evolution in GNNs is not well understood. In this paper, we focus on…

Machine Learning · Computer Science 2023-10-27 Vignesh Kothapalli , Tom Tirer , Joan Bruna

Deep convolutional neural networks (CNNs) used in practice employ potentially hundreds of layers and $10$,$000$s of nodes. Such network sizes entail significant computational complexity due to the large number of convolutions that need to…

Machine Learning · Statistics 2018-03-15 Thomas Wiatowski , Philipp Grohs , Helmut Bölcskei

Our theoretical understanding of deep learning has not kept pace with its empirical success. While network architecture is known to be critical, we do not yet understand its effect on learned representations and network behavior, or how…

Machine Learning · Computer Science 2022-07-22 Andrew M. Saxe , Shagun Sodhani , Sam Lewallen

Understanding the inner working mechanism of deep neural networks (DNNs) is essential and important for researchers to design and improve the performance of DNNs. In this work, the entropy analysis is leveraged to study the neurons…

Computer Vision and Pattern Recognition · Computer Science 2019-11-06 Longwei Wang , Peijie Chen

Deep unrolling, or unfolding, is an emerging learning-to-optimize method that unrolls a truncated iterative algorithm in the layers of a trainable neural network. However, the convergence guarantees and generalizability of the unrolled…

Machine Learning · Computer Science 2024-12-02 Samar Hadou , Navid NaderiAlizadeh , Alejandro Ribeiro

The observed architecture of ecological and socio-economic networks differs significantly from that of random networks. From a network science standpoint, non-random structural patterns observed in real networks call for an explanation of…

Physics and Society · Physics 2019-05-30 Manuel Sebastian Mariani , Zhuo-Ming Ren , Jordi Bascompte , Claudio Juan Tessone

The relationship between the design and functionality of molecular networks is now a key issue in biology. Comparison of regulatory networks performing similar tasks can give insights into how network architecture is constrained by the…

Molecular Networks · Quantitative Biology 2015-06-26 Ala Trusina , Kim Sneppen , Ian B. Dodd , Keith E. Shearwin , J. Barry Egan

The dynamics of noise-resilient Boolean networks with majority functions and diverse topologies is investigated. A wide class of possible topological configurations is parametrized as a stochastic blockmodel. For this class of networks, the…

Disordered Systems and Neural Networks · Physics 2012-01-11 Tiago P. Peixoto

This paper investigates the learnability of the nonlinearity property of Boolean functions using neural networks. We train encoder style deep neural networks to learn to predict the nonlinearity of Boolean functions from examples of…

Machine Learning · Computer Science 2025-02-04 Sriram Ranga , Nandish Chattopadhyay , Anupam Chattopadhyay

We study the role of depth in training randomly initialized overparameterized neural networks. We give a general result showing that depth improves trainability of neural networks by improving the conditioning of certain kernel matrices of…

Machine Learning · Computer Science 2021-02-18 Naman Agarwal , Pranjal Awasthi , Satyen Kale

Functional depth is the functional data analysis technique that orders a functional data set. Unlike the case of data on the real line, defining this order is non-trivial, and particularly, with functional data, there are a number of…

Methodology · Statistics 2022-06-29 Alicia Nieto-Reyes , John A. D. Aston

We perform an empirical study of the behaviour of deep networks when fully linearizing some of its feature channels through a sparsity prior on the overall number of nonlinear units in the network. In experiments on image classification and…

Machine Learning · Computer Science 2023-06-02 Christian H. X. Ali Mehmeti-Göpel , Jan Disselhoff

The promise of discovering a functional blueprint of a cellular system from large-scale and high-throughput sequence and experimental data is predicated on the belief that the same top-down investigative approach that proved successful in…

Molecular Networks · Quantitative Biology 2007-05-23 Riccardo Boscolo , Behnam A. Rezaei , P. Oscar Boykin , Vwani P. Roychowdhury

This research addresses the challenge of characterizing the complexity and unpredictability of basins within various dynamical systems. The main focus is on demonstrating the efficiency of convolutional neural networks (CNNs) in this field.…

Machine Learning · Computer Science 2024-06-18 David Valle , Alexandre Wagemakers , Miguel A. F. Sanjuán

Fourier embedding has shown great promise in removing spectral bias during neural network training. However, it can still suffer from high generalization errors, especially when the labels or measurements are noisy. We demonstrate that…

Machine Learning · Computer Science 2024-09-04 Halyun Jeong , Jihun Han

Regulatory networks describe the interactions between molecular or cellular regulators, like transcription factors and genes in gene regulatory networks, kinases and their receptors in signalling networks, or neurons in neural networks. A…

Molecular Networks · Quantitative Biology 2022-12-29 Niklas Bonacker , Johannes Berg

We investigate the dynamical properties of the transcriptional regulation of gene expression in the yeast Saccharomyces Cerevisiae within the framework of a synchronously and deterministically updated Boolean network model. By means of a…

Molecular Networks · Quantitative Biology 2015-05-13 Murat Tugrul , Alkan Kabakcioglu

We consider efficiency in the implementation of deep neural networks. Hardware accelerators are gaining interest as machine learning becomes one of the drivers of high-performance computing. In these accelerators, the directed graph…

Machine Learning · Computer Science 2021-04-28 George A. Constantinides

We show that deep networks are better than shallow networks at approximating functions that can be expressed as a composition of functions described by a directed acyclic graph, because the deep networks can be designed to have the same…

Machine Learning · Computer Science 2019-11-26 H. N. Mhaskar , T. Poggio

Functional networks provide a topological description of activity patterns in the brain, as they stem from the propagation of neural activity on the underlying anatomical or structural network of synaptic connections. This latter is well…

Disordered Systems and Neural Networks · Physics 2021-02-11 Ali Safari , Paolo Moretti , Ibai Diez , Jesus M. Cortes , Miguel Ángel Muñoz