paper-with-me

홈 › Papers

Metric as Transform: Exploring beyond Affine Transform for Interpretable Neural Network

2024-10-21 · Suman Sapkota

Artificial Neural Networks of varying architectures are generally paired with affine transformation at the core. However, we find dot product neurons with global influence less interpretable as compared to local influence of euclidean distance (as used in Radial Basis Function Network). In this work, we explore the generalization of dot product neurons to $l^p$-norm, metrics, and beyond. We find that metrics as transform performs similarly to affine transform when used in MultiLayer Perceptron or Convolutional Neural Network. Moreover, we explore various properties of Metrics, compare it with Affine, and present multiple cases where metrics seem to provide better interpretability. We develop an interpretable local dictionary based Neural Networks and use it to understand and reject adversarial examples.

📄 PDF Abstract BibTeX arXiv:2410.16159

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Symmetry Discovery Beyond Affine Transformations

2024-06-05 · Ben Shaw, Abram Magner, Kevin R. Moon

Symmetry detection can improve various machine learning tasks. In the context of continuous symmetry detection, current state of the art experiments are limited to detecting affine transformations. Under the manifold ass…

Symmetry Detection

Data Augmentation with Manifold Exploring Geometric Transformations for Increased Performance and Robustness

2019-01-14 · Magdalini Paschali, Walter Simson, Abhijit Guha Roy, Muhammad Ferjad Naeem 외

In this paper we propose a novel augmentation technique that improves not only the performance of deep neural networks on clean test data, but also significantly increases their robustness to random transformations, both…

Data AugmentationGeneral ClassificationLesion ClassificationSkin Lesion Classification

LAG-XAI: A Lie-Inspired Affine Geometric Framework for Interpretable Paraphrasing in Transformer Latent Spaces

2026-04-07 · Olexander Mazurets, Olexander Barmak, Leonid Bedratyuk, Iurii Krak arxiv

Modern Transformer-based language models achieve strong performance in natural language processing tasks, yet their latent semantic spaces remain largely uninterpretable black boxes. This paper introduces LAG-XAI (Lie Af…

Domain Generalization

Riemannian Geometry Approach for Minimizing Distortion and its Applications

2022-07-25 · Dror Ozeri

Given an affine transformation $T$, we define its Fisher distortion $Dist_F(T)$. We show that the Fisher distortion has Riemannian metric structure and provide an algorithm for finding mean distorting transformation -- n…

Affine Invariance in Continuous-Domain Convolutional Neural Networks

2023-11-13 · Ali Mohaddes, Johannes Lederer

The notion of group invariance helps neural networks in recognizing patterns and features under geometric transformations. Group convolutional neural networks enhance traditional convolutional neural networks by incorpor…

Deep Learning