Optical neural networks (ONNs) have attracted great attention due to their low power consumption and high-speed processing. When training an ONN implemented on a chip with possible fabrication variations, the well-known backpropagation algorithm cannot be executed accurately because the perfect information inside the chip cannot be observed. Instead, we employ a black-box optimization method such as zeroth-order (ZO) optimization. In this paper, we first discuss how ONN parameters should be perturbed to search for better values in a black-box manner. Conventionally, parameter perturbations are sampled from a normal distribution with an identity covariance matrix. This is plausible if the parameters are not interrelated in a module, like a linear module of an ordinary neural network. However, this is not the best way for ONN modules with layered parameters, which are interrelated by optical paths. We then propose to perturb the parameters by a normal distribution with a special covariance matrix computed by our novel method. The covariance matrix is designed so that the perturbations appearing at the module output caused by the parameter perturbations become as isotropic as possible to uniformly search for better values. Experimental results show that the proposed method using the special covariance matrix significantly outperformed conventional methods.

With the rapid progress of the integrated nanophotonics technology, the optical neural network (ONN) architecture has been widely investigated. Although the ONN inference is fast, conventional densely connected network structures consume large amounts of power in laser sources. We propose a novel ONN design method that finds an ultrafast, energy-efficient, and accurate ONN structure. The key idea is power-aware edge pruning that derives the near-optimal numbers of edges in the entire network. Optoelectronic circuit simulation demonstrates the correct functional behavior of the ONN. Furthermore, experimental evaluations using tensor-flow show the proposed methods achieved 98.28% power reduction without significant loss of accuracy.

A tamper-resistant logical operation method based on integrated nanophotonics is proposed focusing on electromagnetic side-channel attacks. In the proposed method, only the phase of each optical signal is modulated depending on its logical state, which keeps the power of optical signals in optical logic circuits constant. This provides logic-gate-level tamper resistance which is difficult to achieve with CMOS circuits. An optical implementation method based on electronically-controlled phase shifters is then proposed. The electrical part of proposed circuits achieves 300 times less instantaneous current change, which is proportional to intensity of the leaked electromagnetic wave, than a CMOS logic gate.

Optical circuits using nanophotonic devices attract significant interest due to its ultra-high speed operation. As a consequence, the synthesis methods for the optical circuits also attract increasing attention. However, existing methods for synthesizing optical circuits mostly rely on straight-forward mappings from established data structures such as Binary Decision Diagram (BDD). The strategy of simply mapping a BDD to an optical circuit sometimes results in an explosion of size and involves significant power losses in branches and optical devices. To address these issues, this paper proposes a method for reducing the size of BDD-based optical logic circuits exploiting wavelength division multiplexing (WDM). The paper also proposes a method for reducing the number of branches in a BDD-based circuit, which reduces the power dissipation in laser sources. Experimental results obtained using a partial product accumulation circuit in parallel multipliers demonstrates significant advantages of our method over existing approaches in terms of area and power consumption.

Integrated optical circuits with nanophotonic devices have attracted significant attention due to their low power dissipation and light-speed operation. With light interference and resonance phenomena, the nanophotonic device works as a voltage-controlled optical pass-gate like a pass-transistor. This article first introduces the concept of optical pass-gate logic and then proposes a parallel adder circuit based on optical pass-gate logic. Experimental results obtained with an optoelectronic circuit simulator show the advantages of our optical parallel adder circuit over a traditional CMOS-based parallel adder circuit.

Photonic crystals were proposed over two decades ago to realize strong light confinement via their perfect photonic bandgaps, but the expected ultrahigh-Qwavelength-sized cavities were achieved just recently in a slightly different system that has only a partial bandgap, more specifically, a modulated mode-gap cavity in a 2-D photonic crystal. It is now possible to store photons for over a nanosecond in a wavelength-sized volume for this type of cavity, which has not been realized in other systems. The same confinement mechanism has provided various interesting cavities including air-core cavities, index-modulation-induced cavities, and dynamic cavities. We discuss the impact and possible applications of the achieved strong light confinement. First, it has a strong impact on photonic integrated circuits and photonic network-on-chip (NoC) applications because these cavities enable us to realize tiny, low-power-consumption, and integratable photonic devices, which are hard to realize conventionally. It is next shown that an ultrahigh-Qcavity system constitutes an extreme slow-light medium. It is also shown that ultrahigh-Qcavities enable the adiabatic tuning of light, which makes it possible to manipulate optical signals very differently from conventional optics. Finally, other possible systems promising for strong light confinement are investigated, such as 1-D photonic crystals and photonic amorphous structures without any periodicity.