Zobrazeno 1 - 5
of 5
pro vyhledávání: '"55N31, 68T07"'
This survey provides a comprehensive exploration of applications of Topological Data Analysis (TDA) within neural network analysis. Using TDA tools such as persistent homology and Mapper, we delve into the intricate structures and behaviors of neural
Externí odkaz:
http://arxiv.org/abs/2312.05840
We propose a novel way to improve the generalisation capacity of deep learning models by reducing high correlations between neurons. For this, we present two regularisation terms computed from the weights of a minimum spanning tree of the clique whos
Externí odkaz:
http://arxiv.org/abs/2308.04870
Autor:
Ballester, Rubén, Clemente, Xavier Arnal, Casacuberta, Carles, Madadi, Meysam, Corneanu, Ciprian A., Escalera, Sergio
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 purpose, we
Externí odkaz:
http://arxiv.org/abs/2203.12330
Autor:
Barannikov, Serguei, Trofimov, Ilya, Sotnikov, Grigorii, Trimbach, Ekaterina, Korotin, Alexander, Filippov, Alexander, Burnaev, Evgeny
Publikováno v:
35th Conference on Neural Information Processing Systems (NeurIPS 2021)
We develop a framework for comparing data manifolds, aimed, in particular, towards the evaluation of deep generative models. We describe a novel tool, Cross-Barcode(P,Q), that, given a pair of distributions in a high-dimensional space, tracks multisc
Externí odkaz:
http://arxiv.org/abs/2106.04024
Autor:
Ballester, Rub��n, Clemente, Xavier Arnal, Casacuberta, Carles, Madadi, Meysam, Corneanu, Ciprian A., Escalera, Sergio
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 purpose, we
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::483a7df39e6cb416eb39c77e1630250e
http://arxiv.org/abs/2203.12330
http://arxiv.org/abs/2203.12330