English
Related papers

Related papers: Neural Persistence: A Complexity Measure for Deep …

200 papers

Neural Persistence is a prominent measure for quantifying neural network complexity, proposed in the emerging field of topological data analysis in deep learning. In this work, however, we find both theoretically and empirically that the…

Machine Learning · Computer Science 2023-11-22 Leander Girrbach , Anders Christensen , Ole Winther , Zeynep Akata , A. Sophia Koepke

The learnability of different neural architectures can be characterized directly by computable measures of data complexity. In this paper, we reframe the problem of architecture selection as understanding how data determines the most…

Machine Learning · Computer Science 2018-02-14 William H. Guss , Ruslan Salakhutdinov

Seeking effective neural networks is a critical and practical field in deep learning. Besides designing the depth, type of convolution, normalization, and nonlinearities, the topological connectivity of neural networks is also important.…

Computer Vision and Pattern Recognition · Computer Science 2020-08-20 Kun Yuan , Quanquan Li , Jing Shao , Junjie Yan

Topological features based on persistent homology capture high-order structural information so as to augment graph neural network methods. However, computing extended persistent homology summaries remains slow for large and dense graphs and…

Machine Learning · Computer Science 2022-11-16 Zuoyu Yan , Tengfei Ma , Liangcai Gao , Zhi Tang , Yusu Wang , Chao Chen

While various complexity measures for deep neural networks exist, specifying an appropriate measure capable of predicting and explaining generalization in deep networks has proven challenging. We propose Neural Complexity (NC), a…

Machine Learning · Computer Science 2020-10-26 Yoonho Lee , Juho Lee , Sung Ju Hwang , Eunho Yang , Seungjin Choi

Topological data analysis is an emerging mathematical concept for characterizing shapes in multi-scale data. In this field, persistence diagrams are widely used as a descriptor of the input data, and can distinguish robust and noisy…

Machine Learning · Statistics 2017-06-13 Genki Kusano , Kenji Fukumizu , Yasuaki Hiraoka

Although neural networks are capable of reaching astonishing performances on a wide variety of contexts, properly training networks on complicated tasks requires expertise and can be expensive from a computational perspective. In industrial…

Machine Learning · Statistics 2021-05-11 Théo Lacombe , Yuichi Ike , Mathieu Carriere , Frédéric Chazal , Marc Glisse , Yuhei Umeda

Characterizing the structural properties of neural networks is crucial yet poorly understood, and there are no well-established similarity measures between networks. In this work, we observe that neural networks can be represented as…

Machine Learning · Computer Science 2021-06-01 David Pérez-Fernández , Asier Gutiérrez-Fandiño , Jordi Armengol-Estapé , Marta Villegas

Artificial neural networks can learn complex, salient data features to achieve a given task. On the opposite end of the spectrum, mathematically grounded methods such as topological data analysis allow users to design analysis pipelines…

Machine Learning · Computer Science 2022-12-29 Mattia G. Bergomi , Massimo Ferri , Alessandro Mella , Pietro Vertechi

Prediction and discovery of new materials with desired properties are at the forefront of quantum science and technology research. A major bottleneck in this field is the computational resources and time complexity related to finding new…

We present a new framework to measure the intrinsic properties of (deep) neural networks. While we focus on convolutional networks, our framework can be extrapolated to any network architecture. In particular, we evaluate two network…

Machine Learning · Computer Science 2022-05-10 Alberto Badias , Ashis Banerjee

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

Understanding how neural networks generalize on unseen data is crucial for designing more robust and reliable models. In this paper, we study the generalization gap of neural networks using methods from topological data analysis. For this…

In this paper, we systematically analyze the connecting architectures of recurrent neural networks (RNNs). Our main contribution is twofold: first, we present a rigorous graph-theoretic framework describing the connecting architectures of…

Machine Learning · Computer Science 2016-11-15 Saizheng Zhang , Yuhuai Wu , Tong Che , Zhouhan Lin , Roland Memisevic , Ruslan Salakhutdinov , Yoshua Bengio

Representation learning on graphs is a fundamental problem that can be crucial in various tasks. Graph neural networks, the dominant approach for graph representation learning, are limited in their representation power. Therefore, it can be…

Machine Learning · Computer Science 2025-01-17 Zuoyu Yan , Qi Zhao , Ze Ye , Tengfei Ma , Liangcai Gao , Zhi Tang , Yusu Wang , Chao Chen

Persistent homology, a technique from computational topology, has recently shown strong empirical performance in the context of graph classification. Being able to capture long range graph properties via higher-order topological features,…

Machine Learning · Computer Science 2024-12-20 Rubén Ballester , Bastian Rieck

Graph Neural Networks (GNNs) have become the standard for graph representation learning but remain vulnerable to structural perturbations. We propose a novel framework that integrates persistent homology features with stability…

Machine Learning · Computer Science 2025-12-17 Jelena Losic

Persistent homology is a mathematical tool used for studying the shape of data by extracting its topological features. It has gained popularity in network science due to its applicability in various network mining problems, including…

Algebraic Topology · Mathematics 2023-06-21 Mehmet Emin Aktas , Thu Nguyen , Rakin Riza , Muhammad Ifte Islam , Esra Akbas

One of the central challenges facing modern neuroscience is to explain the ability of the nervous system to coherently integrate information across distinct functional modules in the absence of a central executive. To this end Tononi et al.…

Neurons and Cognition · Quantitative Biology 2010-11-30 L. Barnett , C. L. Buckley , S. Bullock

Computational topology provides a tool, persistent homology, to extract quantitative descriptors from structured objects (images, graphs, point clouds, etc). These descriptors can then be involved in optimization problems, typically as a…

Computational Geometry · Computer Science 2026-03-27 Mathieu Carriere , Yuichi Ike , Théo Lacombe , Naoki Nishikawa
‹ Prev 1 2 3 10 Next ›