paper-with-me

Papers

Exploring the high dimensional geometry of HSI features

2021-03-01 · Wojciech Czaja, Ilya Kavalerov, Weilin Li

We explore feature space geometries induced by the 3-D Fourier scattering transform and deep neural network with extended attribute profiles on four standard hyperspectral images. We examine the distances and angles of class means, the variability of classes, and their low-dimensional structures. These statistics are compared to that of raw features, and our results provide insight into the vastly different properties of these two methods. We also explore a connection with the newly observed deep learning phenomenon of neural collapse.

📄 PDF Abstract BibTeX arXiv:2103.01303

Code (1)

ilyakava/pyfst 공식 구현 tf

Tasks

AttributeVocal Bursts Intensity Prediction

Similar Papers 제목 키워드 기반

Exploring the Manifold of Neural Networks Using Diffusion Geometry

2024-11-19 · Elliott Abel, Andrew J. Steindl, Selma Mazioud, Ellie Schueler 외

Drawing motivation from the manifold hypothesis, which posits that most high-dimensional data lies on or near low-dimensional manifolds, we apply manifold learning to the space of neural networks. We learn manifolds wher…

Dimensionality ReductionHyperparameter OptimizationNeural Architecture Search

Exploring the Geometry and Topology of Neural Network Loss Landscapes

2021-01-31 · Stefan Horoi, Jessie Huang, Bastian Rieck, Guillaume Lajoie 외

Recent work has established clear links between the generalization performance of trained neural networks and the geometry of their loss landscape near the local minima to which they converge. This suggests that qualitat…

Dimensionality Reduction

The Riemannian Geometry of Deep Generative Models

2017-11-21 · Hang Shao, Abhishek Kumar, P. Thomas Fletcher

Deep generative models learn a mapping from a low dimensional latent space to a high-dimensional data space. Under certain regularity conditions, these models parameterize nonlinear manifolds in the data space. In this p…

Translation

High-Dimensional Bayesian Optimization via Nested Riemannian Manifolds

2020-10-21 · NeurIPS 2020 12 · Noémie Jaquier, Leonel Rozo

Despite the recent success of Bayesian optimization (BO) in a variety of applications where sample efficiency is imperative, its performance may be seriously compromised in settings characterized by high-dimensional para…

Bayesian OptimizationGaussian ProcessesVocal Bursts Intensity Prediction

High-Dimensional Bayesian Optimization via Random Projection of Manifold Subspaces

2024-12-21 · Quoc-Anh Hoang Nguyen, The Hung Tran

Bayesian Optimization (BO) is a popular approach to optimizing expensive-to-evaluate black-box functions. Despite the success of BO, its performance may decrease exponentially as the dimensionality increases. A common fr…

Bayesian OptimizationRepresentation Learning