Match!

Topological Data Analysis of Decision Boundaries with Application to Model Selection

Published on Jun 9, 2019 in ICML (International Conference on Machine Learning)
Karthikeyan Natesan Ramamurthy14
Estimated H-index: 14
(IBM),
Kush R. Varshney18
Estimated H-index: 18
(IBM),
Krishnan Mody2
Estimated H-index: 2
(NYU: New York University)
Abstract
  • References (0)
  • Citations (2)
馃摉 Papers frequently viewed together
2005
1 Author (Deng Min)
2009IGARSS: International Geoscience and Remote Sensing Symposium
2 Authors (Guo Jiateng, Wu Lixin)
140 Citations
78% of Scinapse members use related papers. After signing in, all features are FREE.
References0
Newest
Cited By2
Newest
#1Bo Liu (Beijing University of Technology)H-Index: 1
Geometry and topology of decision regions are closely related with classification performance and robustness against adversarial attacks. In this paper, we use differential geometry and topology to explore theoretically the geometrical and topological properties of decision regions produced by deep neural networks (DNNs). The goals are to obtain some geometrical and topological properties of decision regions for given DNN models, and provide some principled guidances to designing and regularizin...
#1Michael Moor (ETH Zurich)H-Index: 3
#2Max HornH-Index: 4
Last. Karsten M. BorgwardtH-Index: 44
view all 4 authors...
We propose a novel approach for preserving topological structures of the input space in latent representations of autoencoders. Using persistent homology, a technique from topological data analysis, we calculate topological signatures of both the input and latent space to derive a topological loss term. Under weak theoretical assumptions, we can construct this loss in a differentiable manner, such that the encoding learns to retain multi-scale connectivity information. We show that our approach ...
1 Citations
#2Apostolos ModasH-Index: 2
Last. Pascal FrossardH-Index: 40
view all 4 authors...
Important insights towards the explainability of neural networks and their properties reside in the formation of their decision boundaries. In this work, we borrow tools from the field of adversarial robustness and propose a new framework that permits to relate the features of the dataset with the distance of data samples to the decision boundary along specific directions. We demonstrate that the inductive bias of deep learning has the tendency to generate classification functions that are invar...
#1Eduardo Paluzo-Hidalgo (University of Seville)H-Index: 1
#2Rocio Gonzalez-Diaz (University of Seville)H-Index: 12
Last. Miguel A. Guti茅rrez-Naranjo (University of Seville)H-Index: 17
view all 3 authors...
The canon of the baroque Spanish literature has been thoroughly studied with philological techniques. The major representatives of the poetry of this epoch are Francisco de Quevedo and Luis de Gongora y Argote. They are commonly classified by the literary experts in two different streams: Quevedo belongs to the Conceptismo and Gongora to the Culteranismo. Besides, traditionally, even if Quevedo is considered the most representative of the Conceptismo, Lope de Vega is also considered to be, at le...
Topological features such as persistence diagrams and their functional approximations like persistence images (PIs) have been showing substantial promise for machine learning and computer vision applications. Key bottlenecks to their large scale adoption are computational expenditure and difficulty in incorporating them in a differentiable architecture. We take an important step in this paper to mitigate these bottlenecks by proposing a novel one-step approach to generate PIs directly from the i...