IIIT-Delhi Institutional Repository

Neural networks with topological data analysis

Show simple item record

dc.contributor.author Kasliwal, Pankhuri
dc.contributor.author Anand, Saket (Advisor)
dc.date.accessioned 2021-05-25T07:17:23Z
dc.date.available 2021-05-25T07:17:23Z
dc.date.issued 2019-11-16
dc.identifier.uri http://repository.iiitd.edu.in/xmlui/handle/123456789/912
dc.description.abstract Convolutional Neural Networks are trained using a gradient descent back propagation technique which trains weights in each layer for the sole goal of minimizing training error. Hence, the resulting weights cannot be directly explained. Using Topological Data Analysis we can get an insight on how the neural network is thinking, specifically by analyzing the activation values of validation images as they pass through each layer. Auto-encoders instead of Convolutional neural networks are better for examining the homology of the data. We control connectivity properties of latent space of an auto encoder by studying a novel loss that is differentiable en_US
dc.language.iso en_US en_US
dc.publisher IIIT-Delhi en_US
dc.subject convolutional neural network, persistence, homology, Persistence diagrams, Toplogical Data Analysis, Auto-encoders, connectivity en_US
dc.title Neural networks with topological data analysis en_US
dc.type Other en_US


Files in this item

This item appears in the following Collection(s)

Show simple item record

Search Repository


Advanced Search

Browse

My Account