HIGHLIGHTS
SUMMARY
In 2014, Tait et_al pioneered a feasible and representative architecture to achieve scalable, cascadable, and reliable photonic neural_networks. Later in 2017, Tait et_al correspondingly contrived a recurrent neural_network on a silicon-photonic prototype, where each neuron, i.e., the core component, is composed of an MRR array, a pair of balanced photodetectors, and a laser source, as illustrated in Fig 9a, b. The weight matrices of the photonic neural_networks can be directly mapped onto MRR arrays, loaded and get fine-tuned at high speed (~ 54 GHz ) through standard electrical control. With this architecture, scaling . . .
If you want to have access to all the content you need to log in!
Thanks :)
If you don't have an account, you can create one here.