Distributed Representations Enable Robust Multi-Timescale Symbolic Computation in Neuromorphic Hardware
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866929672853389312 |
|---|---|
| author | Cotteret, Madison Greatorex, Hugh Renner, Alpha Chen, Junren Neftci, Emre Wu, Huaqiang Indiveri, Giacomo Ziegler, Martin Chicca, Elisabetta |
| author_facet | Cotteret, Madison Greatorex, Hugh Renner, Alpha Chen, Junren Neftci, Emre Wu, Huaqiang Indiveri, Giacomo Ziegler, Martin Chicca, Elisabetta |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2405_01305 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Distributed Representations Enable Robust Multi-Timescale Symbolic Computation in Neuromorphic Hardware Cotteret, Madison Greatorex, Hugh Renner, Alpha Chen, Junren Neftci, Emre Wu, Huaqiang Indiveri, Giacomo Ziegler, Martin Chicca, Elisabetta Neural and Evolutionary Computing Artificial Intelligence 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. |
| title | Distributed Representations Enable Robust Multi-Timescale Symbolic Computation in Neuromorphic Hardware |
| topic | Neural and Evolutionary Computing Artificial Intelligence |
| url | https://arxiv.org/abs/2405.01305 |