English
Related papers

Related papers: Topological derivative approach for deep neural ne…

200 papers

Designing neural networks typically relies on manual trial and error or a neural architecture search (NAS) followed by weight training. The former is time-consuming and labor-intensive, while the latter often discretizes architecture search…

Machine Learning · Computer Science 2025-11-19 Zitong Huang , Mansooreh Montazerin , Ajitesh Srivastava

Deep Neural Networks (DNNs) are generated by sequentially performing linear and non-linear processes. Using a combination of linear and non-linear procedures is critical for generating a sufficiently deep feature space. The majority of…

Computer Vision and Pattern Recognition · Computer Science 2022-07-29 Yufei Hu , Nacim Belkhir , Jesus Angulo , Angela Yao , Gianni Franchi

This work attempts to interpret modern deep (convolutional) networks from the principles of rate reduction and (shift) invariant classification. We show that the basic iterative gradient ascent scheme for optimizing the rate reduction of…

Machine Learning · Computer Science 2020-10-30 Kwan Ho Ryan Chan , Yaodong Yu , Chong You , Haozhi Qi , John Wright , Yi Ma

Deep neural networks (DNNs) have provided brilliant performance across various tasks. However, this success often comes at the cost of unnecessarily large model sizes, high computational demands, and substantial memory footprints.…

Machine Learning · Computer Science 2025-11-26 Shaharyar Ahmed Khan Tareen , Filza Khan Tareen

Traditionally, deep learning algorithms update the network weights whereas the network architecture is chosen manually, using a process of trial and error. In this work, we propose two novel approaches that automatically update the network…

Machine Learning · Computer Science 2018-04-10 Ozan İrsoy , Ethem Alpaydın

In order to choose a neural network architecture that will be effective for a particular modeling problem, one must understand the limitations imposed by each of the potential options. These limitations are typically described in terms of…

Machine Learning · Computer Science 2018-10-02 Jesse Johnson

The ability to learn and adapt in real time is a central feature of biological systems. Neuromorphic architectures demonstrating such versatility can greatly enhance our ability to efficiently process information at the edge. A key…

Machine Learning · Computer Science 2019-11-12 Sandeep Madireddy , Angel Yanguas-Gil , Prasanna Balaprakash

We study an optimal control problem aimed at achieving a desired tradeoff between the network coherence and communication requirements in the distributed controller. Our objective is to add a certain number of edges to an undirected…

Optimization and Control · Mathematics 2018-11-26 Sepideh Hassan-Moghaddam , Mihailo R. Jovanović

Deep learning methods have demonstrated outstanding performances on classification and regression tasks on homogeneous data types (e.g., image, audio, and text data). However, tabular data still pose a challenge, with classic machine…

Machine Learning · Computer Science 2023-11-15 Antonio Briola , Yuanrong Wang , Silvia Bartolucci , Tomaso Aste

We propose a partial differential-integral equation (PDE) framework for deep neural networks (DNNs) and their associated learning problem by taking the continuum limits of both network width and depth. The proposed model captures the…

Optimization and Control · Mathematics 2024-11-12 Peter Markowich , Simone Portaro

The understanding of neural activity patterns is fundamentally linked to an understanding of how the brain's network architecture shapes dynamical processes. Established approaches rely mostly on deviations of a given network from certain…

Neurons and Cognition · Quantitative Biology 2014-09-19 Marc-Thorsten Huett , Marcus Kaiser , Claus C. Hilgetag

Wireless sensor networks (WSNs) are the foundation of the Internet of Things (IoT), and in the era of the fifth generation of wireless communication networks, they are envisioned to be truly ubiquitous, reliable, scalable, and energy…

Signal Processing · Electrical Eng. & Systems 2019-11-01 Xiangyue Meng , Hazer Inaltekin , Brian Krongold

Dense prediction tasks such as depth perception and semantic segmentation are important applications in computer vision that have a concrete topological description in terms of partitioning an image into connected components or estimating a…

Computer Vision and Pattern Recognition · Computer Science 2022-10-26 Deqing Fu , Bradley J. Nelson

We introduce a flexible setup allowing for a neural network to learn both its size and topology during the course of a standard gradient-based training. The resulting network has the structure of a graph tailored to the particular learning…

Machine Learning · Computer Science 2020-07-16 Romuald A. Janik , Aleksandra Nowak

This paper investigates the relationship between the universal approximation property of deep neural networks and topological characteristics of datasets. Our primary contribution is to introduce data topology-dependent upper bounds on the…

Machine Learning · Computer Science 2023-05-29 Sangmin Lee , Jong Chul Ye

For almost 70 years, researchers have typically selected the width of neural networks' layers either manually or through automated hyperparameter tuning methods such as grid search and, more recently, neural architecture search. This paper…

Machine Learning · Computer Science 2026-02-17 Federico Errica , Henrik Christiansen , Viktor Zaverkin , Mathias Niepert , Francesco Alesiani

Network topology inference is a cornerstone problem in statistical analyses of complex systems. In this context, the fresh look advocated here permeates benefits from convex optimization and graph signal processing, to identify the…

Social and Information Networks · Computer Science 2016-04-12 Santiago Segarra , Antonio G. Marques , Gonzalo Mateos , Alejandro Ribeiro

We derive an exact representation of the topological effect on the dynamics of sequence processing neural networks within signal-to-noise analysis. A new network structure parameter, loopiness coefficient, is introduced to quantitatively…

Disordered Systems and Neural Networks · Physics 2008-05-11 Pan Zhang , Yong Chen

We present an approach to adaptively utilize deep neural networks in order to reduce the evaluation time on new examples without loss of accuracy. Rather than attempting to redesign or approximate existing networks, we propose two schemes…

Machine Learning · Computer Science 2017-09-20 Tolga Bolukbasi , Joseph Wang , Ofer Dekel , Venkatesh Saligrama

One of the paramount challenges in neuroscience is to understand the dynamics of individual neurons and how they give rise to network dynamics when interconnected. Historically, researchers have resorted to graph theory, statistics, and…

Neurons and Cognition · Quantitative Biology 2019-02-08 Jean-Baptiste Bardin , Gard Spreemann , Kathryn Hess