English
Related papers

Related papers: Elementary superexpressive activations

200 papers

In this article we present new results on neural networks with linear threshold activation functions. We precisely characterize the class of functions that are representable by such neural networks and show that 2 hidden layers are…

Machine Learning · Computer Science 2023-10-20 Sammy Khalife , Hongyu Cheng , Amitabh Basu

The possibility of approximating a continuous function on a compact subset of the real line by a feedforward single hidden layer neural network with a sigmoidal activation function has been studied in many papers. Such networks can…

Neural and Evolutionary Computing · Computer Science 2016-06-29 Namig J. Guliyev , Vugar E. Ismailov

Considering a family of upper frequently hypercyclic operators we care about the existence of vectors which are upper frequently hypercyclic for any operator of this family. We establish sufficient conditions for a family of operators to…

Functional Analysis · Mathematics 2018-04-17 Monia Mestiri

Motivated by structures that appear in deep neural networks, we investigate nonlinear composite models alternating proximity and affine operators defined on different spaces. We first show that a wide range of activation operators used in…

Optimization and Control · Mathematics 2019-03-19 Patrick L. Combettes , Jean-Christophe Pesquet

A modal logic that is strong enough to fully characterize the behavior of a system is called expressive. Recently, with the growing diversity of systems to be reasoned about (probabilistic, cyber-physical, etc.), the focus shifted to…

Logic in Computer Science · Computer Science 2021-05-24 Yuichi Komorida , Shin-ya Katsumata , Clemens Kupke , Jurriaan Rot , Ichiro Hasuo

We present the soft exponential activation function for artificial neural networks that continuously interpolates between logarithmic, linear, and exponential functions. This activation function is simple, differentiable, and parameterized…

Neural and Evolutionary Computing · Computer Science 2016-02-04 Luke B. Godfrey , Michael S. Gashler

The simulation of human neurons and neurotransmission mechanisms has been realized in deep neural networks based on the theoretical implementations of activation functions. However, recent studies have reported that the threshold potential…

Machine Learning · Computer Science 2023-05-11 Kyungsu Lee , Jaeseung Yang , Haeyun Lee , Jae Youn Hwang

To approximate a simple root of an equation we construct families of iterative maps of higher order of convergence. These maps are based on model functions which can be written as an inner product. The main family of maps discussed is…

Numerical Analysis · Mathematics 2014-05-20 Mário M. Graça

Recent years have witnessed a hot wave of deep neural networks in various domains; however, it is not yet well understood theoretically. A theoretical characterization of deep neural networks should point out their approximation ability and…

Machine Learning · Computer Science 2022-10-28 Gao Zhang , Jin-Hui Wu , Shao-Qun Zhang

In reinforcement learning (RL), agents often operate in partially observed and uncertain environments. Model-based RL suggests that this is best achieved by learning and exploiting a probabilistic model of the world. 'Active inference' is…

Machine Learning · Computer Science 2019-11-26 Alexander Tschantz , Manuel Baltieri , Anil. K. Seth , Christopher L. Buckley

Previous literature on unsupervised learning focused on designing structural priors with the aim of learning meaningful features. However, this was done without considering the description length of the learned representations which is a…

Machine Learning · Computer Science 2024-04-05 Paschalis Bizopoulos , Dimitrios Koutsouris

Variational mean field approximations tend to struggle with contemporary overparametrized deep neural networks. Where a Bayesian treatment is usually associated with high-quality predictions and uncertainties, the practical reality has been…

The classical approach to measure the expressive power of deep neural networks with piecewise linear activations is based on counting their maximum number of linear regions. This complexity measure is quite relevant to understand general…

Machine Learning · Computer Science 2021-02-26 Yuuki Takai , Akiyoshi Sannai , Matthieu Cordonnier

Two families $\mathcal{A}$ and $\mathcal{B}$ of sets are said to be cross-$t$-intersecting if each set in $\mathcal{A}$ intersects each set in $\mathcal{B}$ in at least $t$ elements. An active problem in extremal set theory is to determine…

Combinatorics · Mathematics 2015-12-31 Peter Borg

We consider the problem of extracting entropy by sparse transformations, namely functions with a small number of overall input-output dependencies. In contrast to previous works, we seek extractors for essentially all the entropy without…

Computational Complexity · Computer Science 2012-07-27 Andrej Bogdanov , Siyao Guo

We study the approximation by tensor networks (TNs) of functions from classical smoothness classes. The considered approximation tool combines a tensorization of functions in $L^p([0,1))$, which allows to identify a univariate function with…

Functional Analysis · Mathematics 2024-06-26 Mazen Ali , Anthony Nouy

In this partly expository monograph we develop a general framework for producing uncountable families of exotic actions of certain classically studied groups acting on the circle. We show that if $L$ is a nontrivial limit group then the…

Geometric Topology · Mathematics 2018-10-05 Sang-hyun Kim , Thomas Koberda , Mahan Mj

Artificial neural networks (ANN), typically referred to as neural networks, are a class of Machine Learning algorithms and have achieved widespread success, having been inspired by the biological structure of the human brain. Neural…

Machine Learning · Computer Science 2022-04-08 Murilo Gustineli

I aim to show that models, classification or generating functions, invariances and datasets are algorithmically equivalent concepts once properly defined, and provide some concrete examples of them. I then show that a) neural networks (NNs)…

Machine Learning · Computer Science 2016-12-19 Giulio Ruffini

Recent years have witnessed the introduction and development of extremely fast rational function algorithms. Many ideas in this realm arose from polynomial-based linear-algebraic algorithms. However, polynomial approximation is occasionally…

Numerical Analysis · Mathematics 2025-10-03 James Chok , Geoffrey M. Vasil