paper-with-me

홈 › Papers

SkelEx and BoundEx: Natural Visualization of ReLU Neural Networks

2023-05-09 · Pawel Pukowski, Haiping Lu

Despite their limited interpretability, weights and biases are still the most popular encoding of the functions learned by ReLU Neural Networks (ReLU NNs). That is why we introduce SkelEx, an algorithm to extract a skeleton of the membership functions learned by ReLU NNs, making those functions easier to interpret and analyze. To the best of our knowledge, this is the first work that considers linear regions from the perspective of critical points. As a natural follow-up, we also introduce BoundEx, which is the first analytical method known to us to extract the decision boundary from the realization of a ReLU NN. Both of those methods introduce very natural visualization tool for ReLU NNs trained on low-dimensional data.

📄 PDF Abstract BibTeX arXiv:2305.05562

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

A generalizable large-scale foundation model for musculoskeletal radiographs

2026-02-03 · Shinn Kim, Soobin Lee, Kyoungseob Shin, Han-Soo Kim 외 arxiv

Artificial intelligence (AI) has shown promise in detecting and characterizing musculoskeletal diseases from radiographs. However, most existing models remain task-specific, annotation-dependent, and limited in generaliz…

Self-Supervised LearningFracture detection

Explainable Techniques for Analyzing Flow Cytometry Cell Transformers

2023-07-27 · Florian Kowarsch, Lisa Weijler, Florian Kleber, Matthias Wödlinger 외

Explainability for Deep Learning Models is especially important for clinical applications, where decisions of automated systems have far-reaching consequences. While various post-hoc explainable methods, such as attentio…

Binary Classification

Visualization of Multi-Objective Switched Reluctance Machine Optimization at Multiple Operating Conditions with t-SNE

2019-11-04 · Shen Zhang, Shibo Zhang, Sufei Li, Liang Du 외

The optimization of electric machines at multiple operating points is crucial for applications that require frequent changes on speeds and loads, such as the electric vehicles, to strive for the machine optimal performan…

A Theoretical Explanation for Perplexing Behaviors of Backpropagation-based Visualizations

2018-05-18 · ICML 2018 7 · Weili Nie, Yang Zhang, Ankit Patel

Backpropagation-based visualizations have been proposed to interpret convolutional neural networks (CNNs), however a theory is missing to justify their behaviors: Guided backpropagation (GBP) and deconvolutional network …

Shallow Univariate ReLu Networks as Splines: Initialization, Loss Surface, Hessian, & Gradient Flow Dynamics

2020-08-04 · Justin Sahs, Ryan Pyle, Aneel Damaraju, Josue Ortega Caro 외

Understanding the learning dynamics and inductive bias of neural networks (NNs) is hindered by the opacity of the relationship between NN parameters and the function represented. We propose reparametrizing ReLU NNs as co…

Inductive Bias