Manifold-tiling Localized Receptive Fields are Optimal in Similarity-preserving Neural Networks
Preprint
Abstract
Many neurons in the brain, such as place cells in the rodent hippocampus, have localized receptive fields, i.e., they respond to a small neighborhood of stimulus space. What is the functional significance of such representations and how can they arise? Here, we propose that localized receptive fields emerge in similarity-preserving networks of rectifying neurons that learn low-dimensional manifolds populated by sensory inputs. Numerical simulations of such networks on standard datasets yield manifold-tiling localized receptive fields. More generally, we show analytically that, for data lying on symmetric manifolds, optimal solutions of objectives, from which similarity-preserving networks are derived, have localized receptive fields. Therefore, nonnegative similarity-preserving mapping (NSM) implemented by neural networks can model representations of continuous manifolds in the brain.Keywords
This publication has 28 references indexed in Scilit:
- Why Do Similarity Matching Objectives Lead to Hebbian/Anti-Hebbian Networks?Neural Computation, 2018
- A clustering neural network model of insect olfactionbioRxiv, 2017
- A Hebbian/Anti-Hebbian Neural Network for Linear Subspace Learning: A Derivation from Multidimensional Scaling of Streaming DataNeural Computation, 2015
- A Hebbian/Anti-Hebbian network derived from online non-negative matrix factorization can cluster and discover sparse features2014
- Map Plasticity in Somatosensory CortexScience, 2005
- Critical period plasticity in local cortical circuitsNature Reviews Neuroscience, 2005
- Adaptation-Induced Plasticity of Orientation Tuning in Adult Visual CortexNeuron, 2000
- Cortical Map Reorganization Enabled by Nucleus Basalis ActivityScience, 1998
- Center-Surround Organization of Auditory Receptive Fields in the OwlScience, 1978
- Receptive fields, binocular interaction and functional architecture in the cat's visual cortexThe Journal of Physiology, 1962