1. Distributed Representations Enable Robust Multi-Timescale Symbolic Computation in Neuromorphic Hardware
- Author
-
Cotteret, Madison, Greatorex, Hugh, Renner, Alpha, Chen, Junren, Neftci, Emre, Wu, Huaqiang, Indiveri, Giacomo, Ziegler, Martin, and Chicca, Elisabetta
- Subjects
Computer Science - Neural and Evolutionary Computing ,Computer Science - Artificial Intelligence - Abstract
Programming recurrent spiking neural networks (RSNNs) to robustly perform multi-timescale computation remains a difficult challenge. To address this, we describe a single-shot weight learning scheme to embed robust multi-timescale dynamics into attractor-based RSNNs, by exploiting the properties of high-dimensional distributed representations. We embed finite state machines into the RSNN dynamics by superimposing a symmetric autoassociative weight matrix and asymmetric transition terms, which are each formed by the vector binding of an input and heteroassociative outer-products between states. Our approach is validated through simulations with highly non-ideal weights; an experimental closed-loop memristive hardware setup; and on Loihi 2, where it scales seamlessly to large state machines. This work introduces a scalable approach to embed robust symbolic computation through recurrent dynamics into neuromorphic hardware, without requiring parameter fine-tuning or significant platform-specific optimisation. Moreover, it demonstrates that distributed symbolic representations serve as a highly capable representation-invariant language for cognitive algorithms in neuromorphic hardware., Comment: 15 pages, 6 figures. Supplementary material: 7 pages, 6 figures
- Published
- 2024