Abstract
AbstractRecurrent neural networks (RNNs) can process contextual information such as time series signals and language. But their tracking of internal states is a limiting factor, motivating research on analog implementations in photonics. While photonic unidirectional feedforward neural networks (NNs) have demonstrated big leaps, bi-directional optical RNNs present a challenge: the need for a short-term memory that (i) programmable and coherently computes optical inputs, (ii) minimizes added noise, and (iii) allows scalability. Here, we experimentally demonstrate an optoacoustic recurrent operator (OREO) which meets (i, ii, iii). OREO contextualizes the information of an optical pulse sequence via acoustic waves. The acoustic waves link different optical pulses, capturing their information and using it to manipulate subsequent operations. OREO’s all-optical control on a pulse-by-pulse basis offers simple reconfigurability and is used to implement a recurrent drop-out and pattern recognition of 27 optical pulse patterns. Finally, we introduce OREO as bi-directional perceptron for new classes of optical NNs.
Funder
Max-Planck-Gesellschaft
Deutsche Forschungsgemeinschaft
Studienstiftung des Deutschen Volkes
Publisher
Springer Science and Business Media LLC
Reference71 articles.
1. Yu, Y., Si, X., Hu, C. & Zhang, J. A Review of Recurrent Neural Networks: LSTM Cells and Network Architectures. Neural Comput. 31, 1235–1270 (2019).
2. Salehinejad, H., Sankar, S., Barfett, J., Colak, E. & Valaee, S. Recent Advances in Recurrent Neural Networks. Preprint at https://arxiv.org/abs/1801.01078 (2018).
3. Van Den Oord, A., Kalchbrenner, N. & Kavukcuoglu, K. Pixel recurrent neural networks. In Proceedings of the 33rd International Conference on International Conference on Machine Learning - Volume 48, ICML’16, 1747–1756 (JMLR.org, 2016).
4. Mesnil, G. et al. Using Recurrent Neural Networks for Slot Filling in Spoken Language Understanding. IEEE/ACM Trans. Audio Speech Lang. Process. 23, 530–539 (2015).
5. Donahue, J. et al. Long-Term Recurrent Convolutional Networks for Visual Recognition and Description. IEEE Trans. Pattern Anal. Mach. Intell. 39, 677–691 (2017).