Spike-based symbolic computations on bit strings and numbers

• Published in: bioRxiv
• Main Authors: Kraisnikovic, Ceca, Maass, Wolfgang, Legenstein, Robert
• Format: Paper
• Language: English
• Published: Cold Spring Harbor Cold Spring Harbor Laboratory Press 13.09.2021
• Subjects: Artificial intelligence; Cognitive ability; Computer peripherals; Firing pattern; Firing rate; Mathematical models; Neural coding; Neural networks
• DOI: 10.1101/2021.07.14.452347

The brain uses recurrent spiking neural networks for higher cognitive functions such as symbolic computations, in particular, mathematical computations. We review the current state of research on spike-based symbolic computations of this type. In addition, we present new results which show that surprisingly small spiking neural networks can perform symbolic computations on bit sequences and numbers and even learn such computations using a biologically plausible learning rule. The resulting networks operate in a rather low firing rate regime, where they could not simply emulate artificial neural networks by encoding continuous values through firing rates. Thus, we propose here a new paradigm for symbolic computation in neural networks that provides concrete hypotheses about the organization of symbolic computations in the brain. The employed spike-based network models are the basis for drastically more energy-efficient computer hardware - neuromorphic hardware. Hence, our results can be seen as creating a bridge from symbolic artificial intelligence to energy-efficient implementation in spike-based neuromorphic hardware. Competing Interest Statement The authors have declared no competing interest. Footnotes * Sections about the e-prop learning rule (Section 2.3) and population coding (Section 3.1) are extended, and other minor changes are implemented (e.g., replaced "classification error" with "accuracy" in Section 5.1, and the performance results for the experiments described as prior work (Section 4) are added).