Deep learning with coherent nanophotonic circuits
Citations
3 citations
3 citations
Cites methods from "Deep learning with coherent nanopho..."
...The inference unit of the optical neural network was fabricated and proposed in 2016 [6]....
[...]
3 citations
3 citations
Cites background from "Deep learning with coherent nanopho..."
...Inspired by the well-known speed and energy benefits of photonics that are gradually turning interconnection into the stronghold of optical technologies [5–9], recent research efforts are already attempting to transfer the neuromorphic computing principles over optics [10,11]....
[...]
...The I and Q MZIs are driven by the VI and VQ differential voltages imprinting on the real part of EI and EQ the I and Q signals, respectively, with the phase shifter at its Q branch being controlled by a VPM voltage level to achieve the orthogonality between I and Q via a π/2 phase shift....
[...]
...The respective DC power supplies are employed in order to properly bias the I and Q MZIs as well as to define the 0 or π phase shift at the phase shifter, determining in this way whether addition or subtraction will be carried out between w1x1 and w2x2....
[...]
...Coherent layouts that exploit the phase of the optical carrier electric field for sign encoding purposes can yield single-wavelength and single-laser linear neuron deployments, but have been demonstrated so far only in a rather complex spatial layout for matrix multiplication purposes with multiple cascaded MZIs [10] This design follows the Reck-proposal and requires a N2 number of MZIs for an N-input configuration, scaling quadratically with the fan-in value....
[...]
...Coherent layouts that exploit the phase of the optical carrier electric field for sign encoding purposes can yield single-wavelength and single-laser linear neuron deployments, but have been demonstrated so far only in a rather complex spatial layout for matrix multiplication purposes with multiple cascaded MZIs [10] This design follows the Reck-proposal and requires a N(2) number of MZIs for an N-input configuration, scaling quadratically with the fan-in value....
[...]
3 citations
Cites background from "Deep learning with coherent nanopho..."
...Photonic implementations of DL models are among the most promising approaches for providing very fast and low energy neuromorphic solutions for DL applications [4]....
[...]
References
73,978 citations
[...]
46,982 citations
23,074 citations
"Deep learning with coherent nanopho..." refers background or methods in this paper
...The computational resolution of ONNs is limited by practical non-idealities, including (1) thermal crosstalk between phase shifters in interferometers, (2) optical coupling drift, (3) the finite precision with which an optical phase can be set (16 bits in our case), (4) photodetection noise and (5) finite photodetection dynamic range (30 dB in our case)....
[...]
...(3) Once a neural network is trained, the architecture can be passive, and computation on the optical signals will be performed without additional energy input....
[...]
...We used four instances of the OIU to realize the following matrix transformations in the spatial-mode basis: (1) U((1))Σ((1)), (2) V((1)), (3) U((2))Σ((2)) and (4) V((2))....
[...]
...Transformations (1) and (2) realize the first matrix M((1)), and (3) and (4) implement M((2))....
[...]
16,717 citations
14,635 citations
"Deep learning with coherent nanopho..." refers methods in this paper
...ANNs can be trained by feeding training data into the input layer and then computing the output by forward propagation; weighting parameters in each matrix are subsequently optimized using back propagation [16]....
[...]