Characterizing and Measuring the Similarity of Neural Networks with Persistent Homology
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 abstract simplicial complex and analyzed using their topological 'fingerprints' via Persistent Homology (PH). We then describe a PH-based representation proposed for characterizing and measuring similarity of neural networks. We empirically show the effectiveness of this representation as a descriptor of different architectures in several datasets. This approach based on Topological Data Analysis is a step towards better understanding neural networks and serves as a useful similarity measure.
Code (1)
Tasks
Topological Data AnalysisSimilar Papers 제목 키워드 기반
Mixup Barcodes: Quantifying Geometric-Topological Interactions between Point Clouds
We combine standard persistent homology with image persistent homology to define a novel way of characterizing shapes and interactions between them. In particular, we introduce: (1) a mixup barcode, which captures geomet…
DisentanglementInterpretable Phase Detection and Classification with Persistent Homology
We apply persistent homology to the task of discovering and characterizing phase transitions, using lattice spin models from statistical physics for working examples. Persistence images provide a useful representation of…
ClassificationGeneral ClassificationregressionOn topological data analysis for SHM; an introduction to persistent homology
This paper aims to discuss a method of quantifying the 'shape' of data, via a methodology called topological data analysis. The main tool within topological data analysis is persistent homology; this is a means of measur…
Structural Health MonitoringTopological Data AnalysisHigh-Dimensional Classification for Brain Decoding
Brain decoding involves the determination of a subject's cognitive state or an associated stimulus from functional neuroimaging data measuring brain activity. In this setting the cognitive state is typically characterize…
Brain DecodingClassificationGeneral ClassificationVocal Bursts Intensity PredictionMesh Learning Using Persistent Homology on the Laplacian Eigenfunctions
We use persistent homology along with the eigenfunctions of the Laplacian to study similarity amongst triangulated 2-manifolds. Our method relies on studying the lower-star filtration induced by the eigenfunctions of the…
Topological Data Analysis