paper-with-me

Papers

A Topology Layer for Machine Learning

2019-05-29 · Rickard Brüel-Gabrielsson, Bradley J. Nelson, Anjan Dwaraknath, Primoz Skraba, Leonidas J. Guibas, Gunnar Carlsson

Topology applied to real world data using persistent homology has started to find applications within machine learning, including deep learning. We present a differentiable topology layer that computes persistent homology based on level set filtrations and edge-based filtrations. We present three novel applications: the topological layer can (i) regularize data reconstruction or the weights of machine learning models, (ii) construct a loss on the output of a deep generative network to incorporate topological priors, and (iii) perform topological adversarial attacks on deep networks trained with persistence features. The code (www.github.com/bruel-gabrielsson/TopologyLayer) is publicly available and we hope its availability will facilitate the use of persistent homology in deep learning and other gradient based applications.

📄 PDF Abstract BibTeX arXiv:1905.12200

Code (3)

bruel-gabrielsson/TopologyLayer 공식 구현 pytorch
tlacombe/topt tf
yuanl12/tda_updating_persistence pytorch

Tasks

BIG-bench Machine LearningDeep Learning

Similar Papers 제목 키워드 기반

NeuroFabric: Identifying Ideal Topologies for Training A Priori Sparse Networks

2020-02-19 · ICLR 2020 1 · Mihailo Isakov, Michel A. Kinsy

Long training times of deep neural networks are a bottleneck in machine learning research. The major impediment to fast training is the quadratic growth of both memory and compute requirements of dense and convolutional …

Variational Autoencoder based Metamodeling for Multi-Objective Topology Optimization of Electrical Machines

2022-01-21 · Vivek Parekh, Dominik Flore, Sebastian Schöps

Conventional magneto-static finite element analysis of electrical machine design is time-consuming and computationally expensive. Since each machine topology has a distinct set of parameters, design optimization is commo…

Decoder

Topology guaranteed segmentation of the human retina from OCT using convolutional neural networks

2018-03-14 · Yufan He, Aaron Carass, Bruno M. Jedynak, Sharon D. Solomon 외

Optical coherence tomography (OCT) is a noninvasive imaging modality which can be used to obtain depth images of the retina. The changing layer thicknesses can thus be quantified by analyzing these OCT images, moreover t…

PositionSegmentation

NTopo: Mesh-free Topology Optimization using Implicit Neural Representations

2021-02-22 · NeurIPS 2021 12 · Jonas Zehnder, Yue Li, Stelian Coros, Bernhard Thomaszewski

Recent advances in implicit neural representations show great promise when it comes to generating numerical solutions to partial differential equations. Compared to conventional alternatives, such representations employ …

Self-Supervised Learning

Scalable Training of Artificial Neural Networks with Adaptive Sparse Connectivity inspired by Network Science

2017-07-15 · Decebal Constantin Mocanu, Elena Mocanu, Peter Stone, Phuong H. Nguyen 외

Through the success of deep learning in various domains, artificial neural networks are currently among the most used artificial intelligence methods. Taking inspiration from the network properties of biological neural n…

Sparse Learning