English
Related papers

Related papers: Universal Learning Theory

200 papers

Recent advances in deep learning have allowed Artificial Intelligence (AI) to reach near human-level performance in many sensory, perceptual, linguistic or cognitive tasks. There is a growing need, however, for novel, brain-inspired…

Artificial Intelligence · Computer Science 2021-02-23 Rufin VanRullen , Ryota Kanai

Modern AI is based on deep artificial neural networks (NNs). As of 2025, the most cited scientific article of the 21st century is an NN paper on deep residual learning with residual connections. Who invented this? We present a timeline of…

Machine Learning · Computer Science 2025-09-30 Juergen Schmidhuber

Based on a new theory of causality [1] and its development to the theory of the Universe [2], we show, in this paper, new ideas for building a theory of everything.

General Physics · Physics 2009-09-25 Nguyen Tuan Anh

Over the past two decades machine learning has permeated almost every realm of technology. At the same time, many researchers have begun using category theory as a unifying language, facilitating communication between different scientific…

Machine Learning · Computer Science 2021-06-15 Dan Shiebler , Bruno Gavranović , Paul Wilson

Francis Bacon popularized the idea that science is based on a process of induction by which repeated observations are, in some unspecified way, generalized to theories based on the assumption that the future resembles the past. This idea…

Artificial Intelligence · Computer Science 2021-10-05 Bruce Nielson , Daniel C. Elton

We study shallow and deep neural networks whose inputs range over a general topological space. The model is built from a prescribed family of continuous feature maps and reduces to multilayer feedforward networks in the Euclidean case. We…

General Topology · Mathematics 2026-03-24 Vugar Ismailov

For a given distribution, learning algorithm, and performance metric, the rate of convergence (or data-scaling law) is the asymptotic behavior of the algorithm's test performance as a function of number of train samples. Many learning…

Machine Learning · Computer Science 2021-11-10 Preetum Nakkiran

In this article, we apply some ideas developped by M. Cha{\l}upnik to the framework of strict polynomial bifunctors. This allows us to get a new proof of the existence of the `universal classes' originally constructed by the author.

Representation Theory · Mathematics 2013-02-19 Antoine Touzé

We study the concept of universal sets from the additive--combinatorial point of view. Among other results we obtain some applications of this type of uniformity to sets avoiding solutions to linear equations, and get an optimal upper bound…

Combinatorics · Mathematics 2024-04-03 Ilya D. Shkredov

The first decade of this century has seen the nascency of the first mathematical theory of general artificial intelligence. This theory of Universal Artificial Intelligence (UAI) has made significant contributions to many theoretical,…

Artificial Intelligence · Computer Science 2013-05-17 Marcus Hutter

Deep learning has been widely applied and brought breakthroughs in speech recognition, computer vision, and many other domains. The involved deep neural network architectures and computational issues have been well studied in machine…

Machine Learning · Computer Science 2018-07-23 Ding-Xuan Zhou

The God Almighty Grand Unification Theory proposed by Oyibo to unify all known forces in nature and other possibly unknown force fields has remained controversial not just because of its ambitious claims but also because of its…

General Physics · Physics 2013-07-04 Godfrey E. Akpojotor , Myron W. Echenim

There exists a theory of a single general-purpose learning algorithm which could explain the principles of its operation. This theory assumes that the brain has some initial rough architecture, a small library of simple innate circuits…

Artificial Intelligence · Computer Science 2016-03-30 Kamil Rocki

We resolve an open problem of Hanneke on the subject of universally consistent online learning with non-i.i.d. processes and unbounded losses. The notion of an optimistically universal learning rule was defined by Hanneke in an effort to…

Machine Learning · Statistics 2022-01-25 Moise Blanchard , Romain Cosson , Steve Hanneke

This book introduces a new context for global homotopy theory, i.e., equivariant homotopy theory with universal symmetries. Many important equivariant theories naturally exist not just for a particular group, but in a uniform way for all…

Algebraic Topology · Mathematics 2020-01-13 Stefan Schwede

We introduce and study the universal norm distribution in this paper, which generalizes the concepts of universal ordinary distribution and the universal Euler system. We study the Anderson type resolution of the universal norm distribution…

Number Theory · Mathematics 2007-05-23 Yi Ouyang

This article introduces Universal Quantum Relativity which is a simple Theory of Everything. It relies on an ultimate doctrine that is the absence of absolute existence. This generalizes relativity principles up to a mother quantum theory.…

General Physics · Physics 2011-08-25 Stephane A. Bronoff

We prove a number of results motivated by global questions of uniformity in computability theory, and universality of countable Borel equivalence relations. Our main technical tool is a game for constructing functions on free products of…

Logic · Mathematics 2020-01-20 Andrew S Marks

A physical theory of the world is presented under the unifying principle that all of nature is laid out before us and experienced through the passage of time. The one-dimensional progression in time is opened out into a multi-dimensional…

General Physics · Physics 2016-07-01 David J. Jackson

Humans can learn a variety of concepts and skills incrementally over the course of their lives while exhibiting many desirable properties, such as continual learning without forgetting, forward transfer and backward transfer of knowledge,…

Machine Learning · Computer Science 2020-06-17 Charles X. Ling , Tanner Bohn