SkelEx and BoundEx: Natural Visualization of ReLU Neural Networks
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.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
A generalizable large-scale foundation model for musculoskeletal radiographs
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 detectionExplainable Techniques for Analyzing Flow Cytometry Cell Transformers
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 ClassificationVisualization of Multi-Objective Switched Reluctance Machine Optimization at Multiple Operating Conditions with t-SNE
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
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
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