Distributed Representations Enable Robust Multi-Timescale Symbolic Computation in Neuromorphic Hardware
This work provides a scalable method for embedding symbolic computation in neuromorphic hardware without fine-tuning, addressing a key bottleneck for cognitive algorithms in this domain.
The paper tackles the challenge of programming recurrent spiking neural networks for robust multi-timescale symbolic computation by introducing a single-shot weight learning scheme that embeds finite state machines using distributed representations, validated through simulations, memristive hardware, and Loihi 2 with seamless scaling to large state machines.
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 nonideal 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.