paper-with-me

Papers

Understanding Generalization through Visualizations

2019-06-07 · NeurIPS Workshop ICBINB 2020 12 · W. Ronny Huang, Zeyad Emam, Micah Goldblum, Liam Fowl, Justin K. Terry, Furong Huang, Tom Goldstein

The power of neural networks lies in their ability to generalize to unseen data, yet the underlying reasons for this phenomenon remain elusive. Numerous rigorous attempts have been made to explain generalization, but available bounds are still quite loose, and analysis does not always lead to true understanding. The goal of this work is to make generalization more intuitive. Using visualization methods, we discuss the mystery of generalization, the geometry of loss landscapes, and how the curse (or, rather, the blessing) of dimensionality causes optimizers to settle into minima that generalize well.

📄 PDF Abstract BibTeX arXiv:1906.03291

Code (2)

wronnyhuang/gen-viz 공식 구현 pytorch
genviz2019/genviz pytorch

Similar Papers 제목 키워드 기반

Visualizing the PHATE of Neural Networks

2019-08-07 · NeurIPS 2019 12 · Scott Gigante, Adam S. Charles, Smita Krishnaswamy, Gal Mishne

Understanding why and how certain neural networks outperform others is key to guiding future development of network architectures and optimization methods. To this end, we introduce a novel visualization algorithm that r…

Continual LearningDimensionality Reduction

Can AI agents understand spoken conversations about data visualizations in online meetings?

2025-09-30 · Rizul Sharma, Tianyu Jiang, Seokki Lee, Jillian Aurisano arxiv

In this short paper, we present work evaluating an AI agent's understanding of spoken conversations about data visualizations in an online meeting scenario. There is growing interest in the development of AI-assistants t…

Compositional Scene Understanding through Inverse Generative Modeling

2025-05-27 · Yanbo Wang, Justin Dauwels, Yilun Du

Generative models have demonstrated remarkable abilities in generating high-fidelity visual content. In this work, we explore how generative models can further be used not only to synthesize visual content but also to un…

Scene Understanding

How Well do Feature Visualizations Support Causal Understanding of CNN Activations?

2021-06-23 · NeurIPS 2021 12 · Roland S. Zimmermann, Judy Borowski, Robert Geirhos, Matthias Bethge 외

A precise understanding of why units in an artificial network respond to certain stimuli would constitute a big step towards explainable artificial intelligence. One widely used approach towards this goal is to visualize…

Explainable artificial intelligence

TABLET: A Large-Scale Dataset for Robust Visual Table Understanding

2025-09-25 · Iñigo Alonso, Imanol Miranda, Eneko Agirre, Mirella Lapata arxiv

While table understanding increasingly relies on pixel-only settings, current benchmarks predominantly use synthetic renderings that lack the complexity and visual diversity of real-world tables. Additionally, existing v…