Understanding Generalization through Visualizations
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.
Code (2)
Similar Papers 제목 키워드 기반
Visualizing the PHATE of Neural Networks
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 ReductionCan AI agents understand spoken conversations about data visualizations in online meetings?
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
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 UnderstandingHow Well do Feature Visualizations Support Causal Understanding of CNN Activations?
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 intelligenceTABLET: A Large-Scale Dataset for Robust Visual Table Understanding
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…