현재 위치
Home
Article
The Generative Mind: Internalizing Noise in Brains and Machines
-
- 발행기관
- 선문효정학술연구회 바로가기
-
- 간행물
- The Journal of Sciences and Innovation for Sustainable Peace(구 The journal of Hyojeong Academia) 바로가기
-
- 통권
- Vol. 4 No. 1 (2026.04)바로가기
-
- 페이지
- pp.39-47
-
- 저자
-
- 언어
- 영어(ENG)
-
- URL
- https://www.earticle.net/Article/A484538
※ 기관로그인 시 무료 이용이 가능합니다.
4,000원
원문정보
초록
- 영어
- Historically minimized as an artifact of data corruption or suboptimal sensing, stochastic noise is undergoing a paradigm shift across the cognitive and computational sciences. Traditional deterministic frameworks have treated noise as a strict limitation—an error term to be eliminated to minimize empirical risk. This thought paper challenges the elimination paradigm by examining the functional role of noise in two primary fields: machine learning and neuroscience. We trace the conceptual evolution of noise from ongoing epistemic inquiries regarding its physical nature to pragmatic inquiries regarding its algorithmic utility. In neuroscience, empirical findings of trial-by-trial neuronal and behavioral variability have revealed that the brain actively leverages non-deterministic variance for exploration and predictive coding. In machine learning, the injection of noise has evolved from a structural regularizer preventing catastrophic overfitting in descriptive models into the generative “sampling seed” of modern probabilistic architectures. Ultimately, by applying Ashby’s Principle of Requisite Variety, this paper posits that intelligent systems do not merely tolerate environmental variance; they actively internalize noise as a functional mechanism to perceive, predict, and generalize within an unpredictable world.
목차
Abstract
1. Introduction
2. Modern Conceptualization of Noise
3. Biological Requisite Variety: Endogenous Noise in the Nervous System
3.1. The Phenomenological Source: Synaptic and Behavioral Variance
3.2. The Computational Mechanism: Predictive Coding and Stochastic Inference
4. Engineering Uncertainty: Stochasticity as the Generative Seed
4.1. The Epistemic Barrier: Deterministic Networks and Uncertainty
4.2. Descriptive Models: Structural Regularization for Generalization
4.3. Generative Models: Internalizing Noise to Smooth Manifolds
5. Discussion
References
키워드
Noise Generative model Deep learning Neural variability Requisite variety Neuroscience-inspired artificial intelligence저자
간행물 정보
발행기관
-
- 발행기관명
- 선문효정학술연구회 [Sun Moon Hyojeong Academy Society]
- 설립연도
- 2023
- 분야
- 복합학>학제간연구
- 소개
- Journal of Hyojeong Academia aims to serve as a global platform where researchers and scholars of various disciplines can contribute ideas for our sustainable global community of Co‐existence, Co‐prosperity, and Co‐righteousness. The journal is a multidisciplinary, open‐access, internationally peer‐reviewed academic journal, and it invites all areas of research conducted in the spirit of post materialism including studies centering on God, studies unifying religions and sciences, and studies on all aspects of Co‐existence, Co‐prosperity, and Co‐righteousness.
간행물
-
- 간행물명
- The Journal of Sciences and Innovation for Sustainable Peace(구 The journal of Hyojeong Academia)
- 간기
- 반년간
- pISSN
- 2982-9305
- 수록기간
- 2023~2026
- 십진분류
- KDC 238 DDC 289
이 권호 내 다른 논문 / The Journal of Sciences and Innovation for Sustainable Peace(구 The journal of Hyojeong Academia) Vol. 4 No. 1
피인용수 : 0건 (자료제공 : 네이버학술정보)
함께 이용한 논문 이 논문을 다운로드한 분들이 이용한 다른 논문입니다.
출처 : 네이버학술정보
0개의 논문이 장바구니에 담겼습니다.