4.6 Article

Structured random receptive fields enable informative sensory encodings

Related references

Note: Only part of the references are listed.
Article Computer Science, Artificial Intelligence

Random Features for Kernel Approximation: A Survey on Algorithms, Theory, and Beyond

Fanghui Liu et al.

Summary: This survey reviews the research on random features from the past ten years, summarizing the motivations, characteristics, and contributions of representative algorithms. The theoretical results related to the key question of the number of random features needed for high approximation quality are discussed. The survey also evaluates popular algorithms on large-scale benchmark datasets and explores the relationship between random features and modern deep neural networks. It serves as an introduction to the topic and a guide for practitioners interested in applying algorithms and understanding theoretical results.

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE (2022)

Article Multidisciplinary Sciences

Spectral bias and task-model alignment explain generalization in kernel regression and infinitely wide neural networks

Abdulkadir Canatar et al.

Summary: This study investigates the generalization error of kernel regression using techniques from statistical mechanics to derive an analytical expression applicable to any kernel and data distribution. The research elucidates the inductive bias of kernel regression, explains its compatibility with learning tasks, and points out that more data may impair generalization in certain cases. Canatar et al. propose a predictive theory of generalization in kernel regression that explains various phenomena observed in wide neural networks.

NATURE COMMUNICATIONS (2021)

Article Neurosciences

Single cortical neurons as deep artificial neural networks

David Beniaguev et al.

Summary: Through machine learning, a systematic approach to characterize neurons' input/output mapping complexity has been introduced, highlighting the use of deep neural networks for capturing complex I/O mapping in realistic models of cortical neurons. The study also reveals that synaptic integration in dendritic branches can be conceptualized as pattern matching from a set of spatiotemporal templates, shedding light on the computational complexity of single neurons and the unique architecture of cortical networks.

NEURON (2021)

Review Physiology

Functional diversity from generic encoding in insect campaniform sensilla

Bradley H. Dickerson et al.

Summary: Insect proprioception relies on campaniform sensilla embedded in the exoskeleton to sense strain, particularly for flight control. These sensilla exhibit selectivity towards stimulus features related by a derivative pair, enabling simple control laws. Specialization of campaniform sensilla may derive from stimulus prefiltering and neural specialization, contributing to more complex responses to naturalistic stimuli.

CURRENT OPINION IN PHYSIOLOGY (2021)

Article Computer Science, Artificial Intelligence

Resolution Learning in Deep Convolutional Networks Using Scale-Space Theory

Silvia L. Pintea et al.

Summary: Modern convolutional neural networks often hard-code resolution hyperparameters in the network architecture, making it difficult to adjust, while the proposed N-Jet layer can automatically learn the correct resolution for each layer and performs well under various input sizes.

IEEE TRANSACTIONS ON IMAGE PROCESSING (2021)

Article Neurosciences

Towards the neural population doctrine

Shreya Saxena et al.

CURRENT OPINION IN NEUROBIOLOGY (2019)

Review Behavioral Sciences

Mechanics to pre-process information for the fine tuning of mechanoreceptors

Friedrich G. Barth

JOURNAL OF COMPARATIVE PHYSIOLOGY A-NEUROETHOLOGY SENSORY NEURAL AND BEHAVIORAL PHYSIOLOGY (2019)

Article Multidisciplinary Sciences

High-dimensional geometry of population responses in visual cortex

Carsen Stringer et al.

NATURE (2019)

Article Computer Science, Artificial Intelligence

Biologically plausible deep learning - But how far can we go with shallow networks?

Bernd Illing et al.

NEURAL NETWORKS (2019)

Article Multidisciplinary Sciences

A critique of pure learning and what artificial neural networks can learn from animal brains

Anthony M. Zador

NATURE COMMUNICATIONS (2019)

Article Multidisciplinary Sciences

Toward a unified theory of efficient, predictive, and sparse coding

Matthew Chalk et al.

PROCEEDINGS OF THE NATIONAL ACADEMY OF SCIENCES OF THE UNITED STATES OF AMERICA (2018)

Article Computer Science, Artificial Intelligence

Why Do Similarity Matching Objectives Lead to Hebbian/Anti-Hebbian Networks?

Cengiz Pehlevan et al.

NEURAL COMPUTATION (2018)

Article Multidisciplinary Sciences

Neural-inspired sensors enable sparse, efficient classification of spatiotemporal data

Thomas L. Mohren et al.

PROCEEDINGS OF THE NATIONAL ACADEMY OF SCIENCES OF THE UNITED STATES OF AMERICA (2018)

Article Computer Science, Artificial Intelligence

Capturing the Dynamical Repertoire of Single Neurons with Generalized Linear Models

Alison I. Weber et al.

NEURAL COMPUTATION (2017)

Article Neurosciences

Optimal Degrees of Synaptic Connectivity

Ashok Litwin-Kumar et al.

NEURON (2017)

Article Biology

Neural evidence supports a dual sensory-motor role for insect wings

Brandon Pratt et al.

PROCEEDINGS OF THE ROYAL SOCIETY B-BIOLOGICAL SCIENCES (2017)

Review Neurosciences

Why neurons mix: high dimensionality for higher cognition

Stefano Fusi et al.

CURRENT OPINION IN NEUROBIOLOGY (2016)

Article Zoology

Dipteran Halteres: Perspectives on Function and Integration for a Unique Sensory Organ

Alexandra M. Yarger et al.

INTEGRATIVE AND COMPARATIVE BIOLOGY (2016)

Article Multidisciplinary Sciences

Improved Compressive Sensing of Natural Scenes Using Localized Random Sampling

Victor J. Barranca et al.

SCIENTIFIC REPORTS (2016)

Article Computer Science, Artificial Intelligence

ImageNet Large Scale Visual Recognition Challenge

Olga Russakovsky et al.

INTERNATIONAL JOURNAL OF COMPUTER VISION (2015)

Article Neurosciences

From the neuron doctrine to neural networks

Rafael Yuste

NATURE REVIEWS NEUROSCIENCE (2015)

Review Neurosciences

The receptive field is dead. Long live the receptive field?

Adrienne Fairhall

CURRENT OPINION IN NEUROBIOLOGY (2014)

Article Engineering, Electrical & Electronic

Deep Scattering Spectrum

Joakim Anden et al.

IEEE TRANSACTIONS ON SIGNAL PROCESSING (2014)

Article Neurosciences

Edge-orientation processing in first-order tactile neurons

J. Andrew Pruszynski et al.

NATURE NEUROSCIENCE (2014)

Article Multidisciplinary Sciences

Performance-optimized hierarchical models predict neural responses in higher visual cortex

Daniel L. K. Yamins et al.

PROCEEDINGS OF THE NATIONAL ACADEMY OF SCIENCES OF THE UNITED STATES OF AMERICA (2014)

Article Computer Science, Artificial Intelligence

Invariant Scattering Convolution Networks

Joan Bruna et al.

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE (2013)

Article Multidisciplinary Sciences

Random convergence of olfactory inputs in the Drosophila mushroom body

Sophie J. C. Caron et al.

NATURE (2013)

Review Neurosciences

Compressed Sensing, Sparsity, and Dimensionality in Neuronal Information Processing and Data Analysis

Surya Ganguli et al.

ANNUAL REVIEW OF NEUROSCIENCE, VOL 35 (2012)

Article Mathematics, Applied

Group Invariant Scattering

Stephane Mallat

COMMUNICATIONS ON PURE AND APPLIED MATHEMATICS (2012)

Article Neurosciences

Local Diversity and Fine-Scale Organization of Receptive Fields in Mouse Visual Cortex

Vincent Bonin et al.

JOURNAL OF NEUROSCIENCE (2011)

Article Biochemical Research Methods

Receptive Field Inference with Localized Priors

Mijung Park et al.

PLOS COMPUTATIONAL BIOLOGY (2011)

Article Biochemical Research Methods

From Spiking Neuron Models to Linear-Nonlinear Models

Srdjan Ostojic et al.

PLOS COMPUTATIONAL BIOLOGY (2011)

Article Multidisciplinary Sciences

Encoding properties of haltere neurons enable motion feature detection in a biological gyroscope

Jessica L. Fox et al.

PROCEEDINGS OF THE NATIONAL ACADEMY OF SCIENCES OF THE UNITED STATES OF AMERICA (2010)

Article Behavioral Sciences

A neural basis for gyroscopic force measurement in the halteres of Holorusia

J. L. Fox et al.

JOURNAL OF COMPARATIVE PHYSIOLOGY A-NEUROETHOLOGY SENSORY NEURAL AND BEHAVIORAL PHYSIOLOGY (2008)

Article Computer Science, Artificial Intelligence

A simple white noise analysis of neuronal light responses

EJ Chichilnisky

NETWORK-COMPUTATION IN NEURAL SYSTEMS (2001)