English
Related papers

Related papers: A no-go theorem for one-layer feedforward networks

200 papers

A combinatorial code $\mathcal{C}$ is a collection of subsets of $[n]$, or equivalently a set of points in $\{0,1\}^n$. A morphism of codes is a map from one combinatorial code to another such that the coordinates of points in the image can…

Combinatorics · Mathematics 2026-03-12 Juliann Geraci , Alexander B. Kunin , Alexandra Seceleanu

Predictive coding is an influential model of cortical neural activity. It proposes that perceptual beliefs are furnished by sequentially minimising "prediction errors" - the differences between predicted and observed data. Implicit in this…

Neurons and Cognition · Quantitative Biology 2022-04-07 Alexander Tschantz , Beren Millidge , Anil K Seth , Christopher L Buckley

A fundamental aspect of limitations in learning any computation in neural architectures is characterizing their optimal capacities. An important, widely-used neural architecture is known as autoencoders where the network reconstructs the…

Neurons and Cognition · Quantitative Biology 2017-05-23 Alireza Alemi , Alia Abbara

Neural networks systematically fail at compositional generalization -- producing correct outputs for novel combinations of known parts. We show that this failure is architectural: compositional generalization is equivalent to functoriality…

Machine Learning · Computer Science 2026-03-18 Karen Sargsyan

The backpropagation of error algorithm used to train deep neural networks has been fundamental to the successes of deep learning. However, it requires sequential backward updates and non-local computations, which make it challenging to…

Neural and Evolutionary Computing · Computer Science 2022-02-22 Beren Millidge , Tommaso Salvatori , Yuhang Song , Rafal Bogacz , Thomas Lukasiewicz

Modifications to a neural network's input and output layers are often required to accommodate the specificities of most practical learning tasks. However, the impact of such changes on architecture's approximation capabilities is largely…

Machine Learning · Computer Science 2020-11-10 Anastasis Kratsios , Eugene Bilokopytov

Volumetric brain reconstructions provide an unprecedented opportunity to gain insights into the complex connectivity patterns of neurons in an increasing number of organisms. Here, we model and quantify the complexity of the resulting…

Neurons and Cognition · Quantitative Biology 2024-05-13 Anastasiya Salova , István A. Kovács

The response time of physical computational elements is finite, and neurons are no exception. In hierarchical models of cortical networks each layer thus introduces a response lag. This inherent property of physical dynamical systems…

Neurons and Cognition · Quantitative Biology 2021-10-28 Paul Haider , Benjamin Ellenberger , Laura Kriener , Jakob Jordan , Walter Senn , Mihai A. Petrovici

Shannon's seminal 1948 work gave rise to two distinct areas of research: information theory and mathematical coding theory. While information theory has had a strong influence on theoretical neuroscience, ideas from mathematical coding…

Neurons and Cognition · Quantitative Biology 2015-02-25 Carina Curto , Vladimir Itskov , Katherine Morrison , Zachary Roth , Judy L. Walker

Neural computation in biological and artificial networks relies on the nonlinear summation of many inputs. The structural connectivity matrix of synaptic weights between neurons is a critical determinant of overall network function, but…

Neurons and Cognition · Quantitative Biology 2022-07-01 Tirthabir Biswas , James E. Fitzgerald

Recurrent neural networks excel at temporal tasks and video processing but require energy-intensive sequential memory operations. We demonstrate that multimode optical fibers naturally implement spatiotemporal recurrent computation through…

Optics · Physics 2026-02-24 Dilem Eşlik , Bahadır Utku Kesgin , Uğur Teğin

A conjecture in algorithmic model theory predicts that the model-checking problem for first-order logic is fixed-parameter tractable on a hereditary graph class if and only if the class is monadically dependent. Originating in model theory,…

Combinatorics · Mathematics 2024-03-28 Jan Dreier , Nikolas Mählmann , Szymon Toruńczyk

The architecture of a neural network constrains the potential dynamics that can emerge. Some architectures may only allow for a single dynamic regime, while others display a great deal of flexibility with qualitatively different dynamics…

Combinatorics · Mathematics 2020-08-04 Carina Curto , Christopher Langdon , Katherine Morrison

In comparison to classical shallow representation learning techniques, deep neural networks have achieved superior performance in nearly every application benchmark. But despite their clear empirical advantages, it is still not well…

Machine Learning · Computer Science 2022-01-11 Calvin Murdock , George Cazenavette , Simon Lucey

Universal approximation theorems provide a mathematical explanation for the expressive power of neural networks. They assert that, under mild conditions on the activation function, feedforward neural networks are dense in broad function…

Machine Learning · Computer Science 2026-05-21 Soumendu Sundar Mukherjee , Himasish Talukdar

The comprehension of the mechanisms at the basis of the functioning of complexly interconnected networks represents one of the main goals of neuroscience. In this work, we investigate how the structure of recurrent connectivity influences…

Disordered Systems and Neural Networks · Physics 2019-05-14 Sungmin Hwang , Viola Folli , Enrico Lanza , Giorgio Parisi , Giancarlo Ruocco , Francesco Zamponi

Changing a circuit dynamically, without actually changing the hardware itself, is called reconfiguration, and is of great importance due to its manifold technological applications. Circuit reconfiguration appears to be a feature of the…

Statistical Mechanics · Physics 2024-05-29 Marcelo O. Magnasco

Nonlinear network dynamics are notoriously difficult to understand. Here we study a class of recurrent neural networks called combinatorial threshold-linear networks (CTLNs) whose dynamics are determined by the structure of a directed…

Neurons and Cognition · Quantitative Biology 2021-09-16 Daniela Egas Santander , Stefania Ebli , Alice Patania , Nicole Sanderson , Felicia Burtscher , Katherine Morrison , Carina Curto

The stunning empirical successes of neural networks currently lack rigorous theoretical explanation. What form would such an explanation take, in the face of existing complexity-theoretic lower bounds? A first step might be to show that…

Machine Learning · Computer Science 2017-07-18 Le Song , Santosh Vempala , John Wilmes , Bo Xie

We build on recent work of Yeats, Courtiel, and others involving connected chord diagrams. We first derive from a Hopf-algebraic foundation a class of tree-like functional equations and prove that they are solved by weighted generating…

Combinatorics · Mathematics 2021-04-07 Lukas Nabergall