Text

Shell Theory : A Statistical Model of Reality

The foundational assumption of machine learning is that the data under consideration is separable into classes; while intuitively reasonable, separability constraints have proven remarkably difficult to formulate mathematically. We believe this problem is rooted in the mismatch between existing statistical techniques and commonly encountered data; object representations are typically high dimensional but statistical techniques tend to treat high dimensions a degenerate case. To address this problem, we develop a dedicated statistical framework for machine learning in high dimensions. The framework derives from the observation that object relations form a natural hierarchy; this leads us to model objects as instances of a high dimensional, hierarchal generative processes. Using a distance based statistical technique, also developed in this paper, we show that in such generative processes, instances of each process in the hierarchy, are almost-always encapsulated by a distinctive-shell that excludes almost-all other instances. The result is shell theory, a statistical machine learning framework in which separability constraints (distinctive-shells) are formally derived from the assumed generative process.

Ketersediaan

Informasi Detail

Judul Seri

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE; Vol.44 No.10 Part 1 October 2022

No. Panggil

-

Penerbit

: .,

Deskripsi Fisik

p. 6438-6453

Bahasa

English

ISBN/ISSN

-

Klasifikasi

NONE

Tipe Isi

-

Tipe Media

-

Tipe Pembawa

-

Edisi

-

Subjek

STATISTICS
ANOMALY DETECTION
HIGH DIMENSION
HIERARCHICAL MODELS
INCREMENTAL LEARNING
ONE-CLASS LEARNING
GENERATIVE MODELS
SEMANTIC MANIFOLD
LIFE-LONG LEARNING

Info Detail Spesifik

DOI: 10.1109/TPAMI.2021.3084598

Pernyataan Tanggungjawab

Wen-Yan Lin, Siying Liu, Changhao Ren, Ngai-Man Cheung, Hongdong Li, Yasuyuki Matsushita

Versi lain/terkait

Lampiran Berkas

Komentar