Learning hierarchically-structured concepts

DOI10.1016/J.NEUNET.2021.07.033MaRDI QIDQ6055133zbMATH OpenOpenAlexFDO

Authors Nancy Lynch, Frederik Mallmann-Trenn

Publication date 28 September 2023

Published in Neural Networks (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/1909.04559

zbMATH Keywords

brain-inspired algorithmshierarchical conceptslearning hierarchical conceptsrecognizing hierarchical conceptsrepresenting hierarchical conceptsspiking neural networks

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Knowledge representation (68T30)

Abstract: We study the question of how concepts that have structure get represented in the brain. Specifically, we introduce a model for hierarchically structured concepts and we show how a biologically plausible neural network can recognize these concepts, and how it can learn them in the first place. Our main goal is to introduce a general framework for these tasks and prove formally how both (recognition and learning) can be achieved. We show that both tasks can be accomplished even in presence of noise. For learning, we analyze Oja's rule formally, a well-known biologically-plausible rule for adjusting the weights of synapses. We complement the learning results with lower bounds asserting that, in order to recognize concepts of a certain hierarchical depth, neural networks must have a corresponding number of layers.

Recommendations

• Bayesian Spiking Neurons II: Learning
• A stochastic population approach to the problem of stable recruitment hierarchies in spiking neural networks
• Supervised learning in multilayer spiking neural networks
• SuperSpike: supervised learning in multilayer spiking neural networks
• Fast Sigmoidal Networks via Spiking Neurons

Cites work

• A neuroidal architecture for cognitive computation
• A simplified neuron model as a principal component analyzer
• Computational tradeoffs in biological neural networks: self-stabilizing winner-take-all networks
• Concentration of Measure for the Analysis of Randomized Algorithms
• scientific article; zbMATH DE number 826255 (Why is no real title available?)
• Long term memory and the densest K-subgraph problem
• Lower Bounds for the Computational Power of Networks of Spiking Neurons
• Memorization and Association on a Realistic Neural Model
• Memory Capacities for Synaptic and Structural Plasticity
• Random projection in the brain and computation with assemblies of neurons
• Random Sketching, Clustering, and Short-Term Memory in Spiking Neural Networks.
• Spike-Based Winner-Take-All Computation: Fundamental Limits and Order-Optimal Circuits
• Spiking Neuron Models
• The hippocampus as a stable memory allocator for cortex

Cited in

(8)

• A formal model of hierarchical concept learning
• A stochastic population approach to the problem of stable recruitment hierarchies in spiking neural networks
• Segmenting state into entities and its implication for Learning
• scientific article; zbMATH DE number 1706378 (Why is no real title available?)
• A low-order model of biological neural networks
• Hierarchically structured neural networks: A way to shape a `magma' of neurons
• A basic compositional model for spiking neural networks
• Learning hierarchically-structured concepts. II: Overlapping concepts, and networks with feedback

This page was built for publication: Learning hierarchically-structured concepts

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6055133)