
TL;DR
This paper introduces a neuro-symbolic model using spiking neural networks to create, bind, unbind, and manipulate symbolic representations called prime attractors, enabling a form of working memory and symbolic computation.
Contribution
It proposes a novel neuro-symbolic framework where prime attractors serve as symbols, supporting binding, unbinding, and memory operations within spiking neural networks.
Findings
Prime attractors act as atomic symbols in neural networks.
Winner-take-all mechanism enables recovery of symbols in noisy signals.
The model demonstrates basic symbolic operations like binding and unbinding.
Abstract
Neural networks promote a distributed representation with no clear place for symbols. Despite this, we propose that symbols are manufactured simply by training a sparse random noise as a self-sustaining attractor in a feedback spiking neural network. This way, we can generate many of what we shall call prime attractors, and the networks that support them are like registers holding a symbolic value, and we call them registers. Like symbols, prime attractors are atomic and devoid of any internal structure. Moreover, the winner-take-all mechanism naturally implemented by spiking neurons enables registers to recover a prime attractor within a noisy signal. Using this faculty, when considering two connected registers, an input one and an output one, it is possible to bind in one shot using a Hebbian rule the attractor active on the output to the attractor active on the input. Thus, whenever…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Code & Models
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsAdvanced Memory and Neural Computing · Neural dynamics and brain function · Ferroelectric and Negative Capacitance Devices
