中文
相关论文

相关论文: Information theory and learning: a physical approa…

200 篇论文

One of the main challenges in the field of embodied artificial intelligence is the open-ended autonomous learning of complex behaviours. Our approach is to use task-independent, information-driven intrinsic motivation(s) to support…

人工智能 · 计算机科学 2013-09-27 Keyan Zahedi , Georg Martius , Nihat Ay

The reliable prediction of the temporal behavior of complex systems is key in numerous scientific fields. This strong interest is however hindered by modeling issues: often, the governing equations describing the physics of the system under…

机器学习 · 计算机科学 2023-05-29 Alessandro Bucci , Onofrio Semeraro , Alexandre Allauzen , Sergio Chibbaro , Lionel Mathelin

Many biological phenomena or social events critically depend on how information evolves in complex networks. However, a general theory to characterize information evolution is yet absent. Consequently, numerous unknowns remain about the…

生物物理 · 物理学 2022-07-20 Yang Tian , Guoqi Li , Pei Sun

A Bayesian network is a graphical model that encodes probabilistic relationships among variables of interest. When used in conjunction with statistical techniques, the graphical model has several advantages for data analysis. One, because…

机器学习 · 计算机科学 2022-01-11 David Heckerman

In the information-based paradigm of inference, model selection is performed by selecting the candidate model with the best estimated predictive performance. The success of this approach depends on the accuracy of the estimate of the…

机器学习 · 统计学 2018-06-11 Colin H. LaMont , Paul A. Wiggins

Learning and the ability to learn are important factors in development and evolutionary processes [1]. Depending on the level, the complexity of learning can strongly vary. While associative learning can explain simple learning behaviour…

神经元与认知 · 定量生物学 2007-05-23 Reimer Kuehn , Ion-Olimpiu Stamatescu

There are (at least) three approaches to quantifying information. The first, algorithmic information or Kolmogorov complexity, takes events as strings and, given a universal Turing machine, quantifies the information content of a string as…

信息论 · 计算机科学 2011-11-29 David Balduzzi

The fact that accurately predicted information can serve as an energy source paves the way for new approaches to autonomous learning. The energy derived from a sequence of successful predictions can be recycled as an immediate incentive and…

新兴技术 · 计算机科学 2024-07-09 Alex Ushveridze

Information Theory provides a fundamental basis for analysis, and for a variety of subsequent methodological approaches, in relation to uncertainty quantification. The transversal character of concepts and derived results justifies its…

统计理论 · 数学 2024-11-27 Jose M. Angulo , Francisco J. Esquivel , Ana E. Madrid , Francisco J. Alonso

Bayesian inference is often utilized for uncertainty quantification tasks. A recent analysis by Xu and Raginsky 2022 rigorously decomposed the predictive uncertainty in Bayesian inference into two uncertainties, called aleatoric and…

机器学习 · 统计学 2023-07-25 Futoshi Futami , Tomoharu Iwata

An information-theoretic framework is introduced to analyze last-layer embedding, focusing on learned representations for regression tasks. We define representation-rate and derive limits on the reliability with which input-output…

信息论 · 计算机科学 2026-05-27 Deborah Pereg , Michael Wand

Prediction of events is the challenge in many different disciplines, from meteorology to finance; the more this task is difficult, the more a system is {\it complex}. Nevertheless, even according to this restricted definition, a general…

chao-dyn · 物理学 2007-05-23 Maurizio Serva

Unsupervised learning plays an important role in many fields, such as artificial intelligence, machine learning, and neuroscience. Compared to static data, methods for extracting low-dimensional structure for dynamic data are lagging. We…

机器学习 · 计算机科学 2022-03-07 Rui Meng , Tianyi Luo , Kristofer Bouchard

Information theory is a mathematical theory of learning with deep connections with topics as diverse as artificial intelligence, statistical physics, and biological evolution. Many primers on information theory paint a broad picture with…

信息论 · 计算机科学 2019-03-26 Philip Chodrow

Existing work on understanding deep learning often employs measures that compress all data-dependent information into a few numbers. In this work, we adopt a perspective based on the role of individual examples. We introduce a measure of…

机器学习 · 计算机科学 2021-06-21 Robert J. N. Baldock , Hartmut Maennel , Behnam Neyshabur

We have a lot of relation to the encoding and the Theory of Information, when considering thinking. This is a natural process and, at once, the complex thing we investigate. This always was a challenge - to understand how our mind works,…

人工智能 · 计算机科学 2012-12-27 Kirill A. Sorudeykin

Can we learn more from data than existed in the generating process itself? Can new and useful information be constructed from merely applying deterministic transformations to existing data? Can the learnable content in data be evaluated…

机器学习 · 计算机科学 2026-03-17 Marc Finzi , Shikai Qiu , Yiding Jiang , Pavel Izmailov , J. Zico Kolter , Andrew Gordon Wilson

Conformal Prediction (CP) is a distribution-free uncertainty estimation framework that constructs prediction sets guaranteed to contain the true answer with a user-specified probability. Intuitively, the size of the prediction set encodes a…

机器学习 · 计算机科学 2025-02-18 Alvaro H. C. Correia , Fabio Valerio Massoli , Christos Louizos , Arash Behboodi

We introduce a class of information measures based on group entropies, allowing us to describe the information-theoretical properties of complex systems. These entropic measures are nonadditive, and are mathematically deduced from a series…

统计力学 · 物理学 2019-10-21 Piergiulio Tempesta , Henrik Jeldtoft Jensen

All natural things process and transform information. They receive environmental information as input, and transform it into appropriate output responses. Much of science is dedicated to building models of such systems -- algorithmic…

量子物理 · 物理学 2017-02-14 Jayne Thompson , Andrew J. P. Garner , Vlatko Vedral , Mile Gu