paper-with-me

Papers

Classification and Geometry of General Perceptual Manifolds

2017-10-17 · SueYeon Chung, Daniel D. Lee, Haim Sompolinsky

Perceptual manifolds arise when a neural population responds to an ensemble of sensory signals associated with different physical features (e.g., orientation, pose, scale, location, and intensity) of the same perceptual object. Object recognition and discrimination requires classifying the manifolds in a manner that is insensitive to variability within a manifold. How neuronal systems give rise to invariant object classification and recognition is a fundamental problem in brain theory as well as in machine learning. Here we study the ability of a readout network to classify objects from their perceptual manifold representations. We develop a statistical mechanical theory for the linear classification of manifolds with arbitrary geometry revealing a remarkable relation to the mathematics of conic decomposition. Novel geometrical measures of manifold radius and manifold dimension are introduced which can explain the classification capacity for manifolds of various geometries. The general theory is demonstrated on a number of representative manifolds, including L2 ellipsoids prototypical of strictly convex manifolds, L1 balls representing polytopes consisting of finite sample points, and orientation manifolds which arise from neurons tuned to respond to a continuous angle variable, such as object orientation. The effects of label sparsity on the classification capacity of manifolds are elucidated, revealing a scaling relation between label sparsity and manifold radius. Theoretical predictions are corroborated by numerical simulations using recently developed algorithms to compute maximum margin solutions for manifold dichotomies. Our theory and its extensions provide a powerful and rich framework for applying statistical mechanics of linear classification to data arising from neuronal responses to object stimuli, as well as to artificial deep networks trained for object recognition tasks.

📄 PDF Abstract BibTeX arXiv:1710.06487

Code (0)

등록된 구현이 없습니다.

Tasks

ClassificationGeneral ClassificationObjectObject Recognition

Similar Papers 제목 키워드 기반

Predicting and Enhancing the Fairness of DNNs with the Curvature of Perceptual Manifolds

2023-03-22 · CVPR 2023 1 · Yanbiao Ma, Licheng Jiao, Fang Liu, Maoji Wen 외

To address the challenges of long-tailed classification, researchers have proposed several approaches to reduce model bias, most of which assume that classes with few samples are weak classes. However, recent studies hav…

ClassificationFairnessLong-tail Learning

Revealing Bias Formation in Deep Neural Networks Through the Geometric Mechanisms of Human Visual Decoupling

2025-02-17 · Yanbiao Ma, Bowei Liu, Wei Dai, Jiayi Chen 외

Deep neural networks (DNNs) often exhibit biases toward certain categories during object recognition, even under balanced training data conditions. The intrinsic mechanisms underlying these biases remain unclear. Inspire…

ObjectObject Recognition

Aristotelian Manifolds: Leveraging Platonic Perceptual Features for Backpropagation Free Rapid Concept Learning

2026-08-21 · Michael Karnes, Alper Yilmaz arxiv

This paper formalizes and systematically characterizes Aristotelian Manifolds, a generalized structural framework built upon the Platonic Representation Hypothesis. We position high-capacity foundation models as universa…

Dimensionality Reduction

Statistical Mechanics of Neural Processing of Object Manifolds

2021-06-01 · SueYeon Chung

Invariant object recognition is one of the most fundamental cognitive tasks performed by the brain. In the neural state space, different objects with stimulus variabilities are represented as different manifolds. In this…

ObjectObject Recognition

Building Neural Networks on Matrix Manifolds: A Gyrovector Space Approach

2023-05-08 · Xuan Son Nguyen, Shuo Yang

Matrix manifolds, such as manifolds of Symmetric Positive Definite (SPD) matrices and Grassmann manifolds, appear in many applications. Recently, by applying the theory of gyrogroups and gyrovector spaces that is a power…

Action RecognitionKnowledge Graph CompletionTemporal Action Localization