Addressing Limited Weight Resolution in a Fully Optical Neuromorphic Reservoir Computing Readout
This addresses a key obstacle for realizing fully optical neuromorphic computers, offering a solution to improve hardware efficiency in high-speed, low-power applications.
The paper tackles the problem of limited weight resolution in optical neuromorphic computing by proposing a new method that improves performance despite noise and low resolution, achieving bit error rates several orders of magnitude better than traditional low-resolution weighting and close to full-resolution performance with only 8 to 32 levels.
Using optical hardware for neuromorphic computing has become more and more popular recently due to its efficient high-speed data processing capabilities and low power consumption. However, there are still some remaining obstacles to realizing the vision of a completely optical neuromorphic computer. One of them is that, depending on the technology used, optical weighting elements may not share the same resolution as in the electrical domain. Moreover, noise and drift are important considerations as well. In this article, we investigate a new method for improving the performance of optical weighting, even in the presence of noise and in the case of very low resolution. Even with only 8 to 32 levels of resolution, the method can outperform the naive traditional low-resolution weighting by several orders of magnitude in terms of bit error rate and can deliver performance very close to full-resolution weighting elements, also in noisy environments.