English
Related papers

Related papers: Convexity of Neural Codes with Four Maximal Codewo…

200 papers

A major area in neuroscience research is the study of how the brain processes spatial information. Neurons in the brain represent external stimuli via neural codes. These codes often arise from stereotyped stimulus-response maps,…

Neurons and Cognition · Quantitative Biology 2016-10-03 Ethan Petersen , Nora Youngs , Ryan Kruse , Dane Miyata , Rebecca Garcia , Luis David Garcia Puente

Deep learning researchers commonly suggest that converged models are stuck in local minima. More recently, some researchers observed that under reasonable assumptions, the vast majority of critical points are saddle points, not true minima.…

Machine Learning · Computer Science 2016-02-25 Zachary C. Lipton

According to parallel distributed processing (PDP) theory in psychology, neural networks (NN) learn distributed rather than interpretable localist representations. This view has been held so strongly that few researchers have analysed…

Neural and Evolutionary Computing · Computer Science 2018-06-12 Ella M. Gale , Nicolas Martin , Jeffrey S. Bowers

In many animal sensory pathways, the transformation from external stimuli to spike trains is essentially deterministic. In this context, a new mathematical framework for coding and reconstruction, based on a biologically plausible model of…

Neurons and Cognition · Quantitative Biology 2019-08-01 Anik Chattopadhyay , Arunava Banerjee

Although artificial neural networks have shown great promise in applications including computer vision and speech recognition, there remains considerable practical and theoretical difficulty in optimizing their parameters. The seemingly…

Machine Learning · Computer Science 2016-12-30 Blaine Rister , Daniel L Rubin

Saddle-point models arise throughout optimization, optimal transport, robust learning, and control. In many applications, the relevant function f(x,y) is convex in x and concave in y, and preserving this geometry is essential for obtaining…

Optimization and Control · Mathematics 2026-05-29 Xavier Warin

We use the embedding formalism to construct conformal fields in $D$ dimensions, by restricting Lorentz-invariant ensembles of homogeneous neural networks in $(D+2)$ dimensions to the projective null cone. Conformal correlators may be…

High Energy Physics - Theory · Physics 2025-10-07 James Halverson , Joydeep Naskar , Jiahua Tian

We establish upper bounds for the expected excess risk of models trained by proper iterative algorithms which approximate the local minima. Unlike the results built upon the strong globally strongly convexity or global growth conditions…

Machine Learning · Computer Science 2022-10-11 Mingyang Yi , Ruoyu Wang , Zhi-Ming Ma

We consider a network of two nodes separated by a noisy channel, in which the input and output signals have to be coordinated with the source and its reconstruction. In the case of strictly causal encoding and non-causal decoding, we prove…

Information Theory · Computer Science 2018-10-15 Giulia Cervia , Laura Luzzi , Maël Le Treust , Matthieu R. Bloch

The Nearest Neighbor (NN) Representation is an emerging computational model that is inspired by the brain. We study the complexity of representing a neuron (threshold function) using the NN representations. It is known that two anchors (the…

Computational Complexity · Computer Science 2024-05-13 Kordag Mehmet Kilic , Jin Sima , Jehoshua Bruck

The push-forward operation enables one to redistribute a probability measure through a deterministic map. It plays a key role in statistics and optimization: many learning problems (notably from optimal transport, generative modeling, and…

Machine Learning · Statistics 2025-05-19 Lucas de Lara , Mathis Deronzier , Alberto González-Sanz , Virgile Foy

The sigmoidal tuning curve that maximizes the mutual information for a Poisson neuron, or population of Poisson neurons, is obtained. The optimal tuning curve is found to have a discrete structure that results in a quantization of the input…

Neurons and Cognition · Quantitative Biology 2009-09-24 Alexander P. Nikitin , Nigel G. Stocks , Robert P. Morse , Mark D. McDonnell

This paper presents a new deep learning-based framework for robust nonlinear estimation and control using the concept of a Neural Contraction Metric (NCM). The NCM uses a deep long short-term memory recurrent neural network for a global…

Systems and Control · Electrical Eng. & Systems 2020-11-20 Hiroyasu Tsukamoto , Soon-Jo Chung

The problem of neural coding is to understand how sequences of action potentials (spikes) are related to sensory stimuli, motor outputs, or (ultimately) thoughts and intentions. One clear question is whether the same coding rules are used…

Neurons in the brain are often finely tuned for specific task variables. Moreover, such disentangled representations are highly sought after in machine learning. Here we mathematically prove that simple biological constraints on neurons,…

Neurons and Cognition · Quantitative Biology 2023-04-04 James C. R. Whittington , Will Dorrell , Surya Ganguli , Timothy E. J. Behrens

Hyperplane codes are a class of convex codes that arise as the output of a one layer feed-forward neural network. Here we establish several natural properties of stable hyperplane codes in terms of the {\it polar complex} of the code, a…

Neurons and Cognition · Quantitative Biology 2019-02-05 Vladimir Itskov , Alex Kunin , Zvi Rosen

We introduce a new neural architecture and an unsupervised algorithm for learning invariant representations from temporal sequence of images. The system uses two groups of complex cells whose outputs are combined multiplicatively: one that…

Neural and Evolutionary Computing · Computer Science 2010-06-03 Karo Gregor , Yann LeCun

Necessary and sufficient conditions for convexity and strong convexity, respectively, of sublevel sets that are defined by finitely many real-valued $C^{1,1}$-maps are presented. A novel characterization of strongly convex sets in terms of…

Optimization and Control · Mathematics 2017-01-03 Alexander Weber , Gunther Reissig

Grid cells in the entorhinal cortex, together with head direction, place, speed and border cells, are major contributors to the organization of spatial representations in the brain. In this work we introduce a novel theoretical and…

Neurons and Cognition · Quantitative Biology 2019-07-25 Fabio Anselmi , Micah M. Murray , Benedetta Franceschiello

This note is a brief survey of some results of the recent collaboration of neurobiologists and mathematicians dedicated to stimulus reconstruction from neuronal spiking activity. This collaboration, in particular, led to the consideration…

History and Overview · Mathematics 2015-01-06 Yuri I. Manin