Krishan Harkhoe

Photonic reservoir computing has been demonstrated to be able to solve various complex problems. Although training a reservoir computing system is much simpler compared to other neural network approaches, it still requires considerable amounts of resources which becomes an issue when retraining is required. Transfer learning is a technique that allows us to re‐use information between tasks, thereby reducing the cost of retraining. We propose transfer learning as a viable technique to compensate for the unavoidable parameter drift in experimental setups. Solving this parameter drift usually requires retraining the system, which is very time and energy consuming. Based on numerical studies on a delay‐based reservoir computing system with semiconductor lasers, we investigate the use of transfer learning to mitigate these parameter fluctuations. Additionally, we demonstrate that transfer learning applied to two slightly different tasks allows us to reduce the amount of input samples required for training of the second task, thus reducing the amount of retraining.

SPIE Digital Library Proceedings

In photonic reservoir computing, semiconductor lasers with delayed feedback have shown to be suited to efficiently solve difficult and time-consuming problems. The input data in this system is often optically injected into the reservoir. Based on numerical simulations, we show that the performance depends heavily on the way that information is encoded in this optical injection signal. In our simulations we compare different input configurations consisting of Mach-Zehnder modulators and phase modulators for injecting the signal. We observe far better performance on a one-step ahead time-series prediction task when modulating the phase of the injected signal rather than only modulating its amplitude.

Multiple photonic systems show great promise for providing practical yet powerful hardware substrates for neuromorphic computing. Among those, delay-based systems offer -through a time-multiplexing technique - a simple technological implementation route. We discuss our advances in the development of passive coherent fibre-ring cavities and semiconductor lasers with integrated delay for reservoir computing. Time-multiplexed systems are also highly suitable for coherent Ising machines as they allow to implement a fully interconnected large scale system with few components. We have recently proposed a system based on opto-electronic oscillators subjected to self-feedback with improved calculation time and solution quality.

Delay-based reservoir computing (RC), a neuromorphic computing technique, has gathered lots of interest, as it promises compact and high-speed RC implementations. To further boost the computing speeds, we introduce and study an RC setup based on spin-VCSELs, thereby exploiting the high polarization modulation speed inherent to these lasers. Based on numerical simulations, we benchmarked this setup against state-of-the-art delay-based RC systems and its parameter space was analyzed for optimal performance. The high modulation speed enabled us to have more virtual nodes in a shorter time interval. However, we found that at these short time scales, the delay time and feedback rate heavily influence the nonlinear dynamics. Therefore, and contrary to other laser-based RC systems, the delay time has to be optimized in order to obtain good RC performances. We achieved state-of-the-art performances on a benchmark timeseries prediction task. This spin-VCSEL-based RC system shows a ten-fold improvement in processing speed, which can further be enhanced in a straightforward way by increasing the birefringence of the VCSEL chip.

Currently, multiple photonic reservoir computing systems show great promise for providing a practical yet powerful hardware substrate for neuromorphic computing. Among those, delay-based systems offer a simple technological route to implement photonic neuromorphic computation. Its operation boils down to a time-multiplexing with the delay length limiting the processing speed. As most optical setups end up to be bulky employing long fiber loops or free-space optics, the processing speeds are ranging from kSa/s to tens of MSa/s. Therefore, we focus on external cavities which are far shorter than what has been realized before in such experiments. We present experimental results of reservoir computing based on a semiconductor laser, operating in a single mode regime around 1550nm, with a 10.8cm delay line. Both are integrated on an active/passive InP photonic chip built on the Jeppix platform. Using 23 virtual nodes spaced 50 ps apart in the integrated delay section, we increase the processing speed to 0.87GSa/s. The computational performance is benchmarked on a forecasting task applied to chaotic time samples. Competitive performance is observed for injection currents above threshold, with higher pumps having lower prediction errors. The feedback strength can be controlled by electrically pumping integrated amplifiers within the delay section. Nevertheless, we find good performance even when these amplifiers are unpumped. To proof the relevance and necessity of the external cavity on the computational capacity, we have analysed linear and nonlinear memory tasks. We also propose several post-processing methods, which increase the performance without a penalty to speed.

Reservoir computing (RC) has reinvigorated neuromorphic computing activities in photonics. RC radically reduces the required complexity for a hardware implementation in photonics as compared to earlier efforts in the nineties. Currently, multiple photonic RC systems show great promise for providing a practical yet powerful hardware substrate for neuromorphic computing. Among those, delay-based systems offer through a time-multiplexing technique a simple technological route to implement photonic neuromorphic computation. We will review the state of the art on delay-based RC and discuss our advances in substrates implemented as passive coherent fibre-ring cavities and semiconductor lasers with delayed optical feedback. Passive coherent reservoirs built using fiber loops have achieved record performances, but are still aided by nonlinear electro-optical transformations at the input and output. Nevertheless, when targeting all-optical reservoirs, these nonlinearities will be absent. We have found that optical nonlinearities in the fibre itself can be sufficient to enhance the task solving capabilities of a passive reservoir. Also, delay-based optical substrates for RC tend to be quite bulky employing long fiber loops or free-space optics. As a result, the processing speeds are limited in the range of kSa/s to tens of MSa/s. We have studied and developed substrates using external cavities which are far shorter than what has been realized before in experiment. Specifically, by integrating a semiconductor laser together with a 10.8 cm delay line on an active/passive InP photonic chip using the Jeppix platform, we can increase the processing speed to GSa/s.

Photonic delay-based reservoir computing (RC) has gained considerable attention lately, as it allows for simple technological implementations of the RC concept that can operate at high speed. In this paper, we discuss a practical, compact and robust implementation of photonic delay-based RC, by integrating a laser and a 5.4 cm delay line on an InP photonic integrated circuit. We demonstrate the operation of this chip with 23 nodes at a speed of 0.87 GSa/s, showing performances that is similar to previous non-integrated delay-based setups. We also investigate two other post-processing methods to obtain more nodes in the output layer. We show that these methods improve the performance drastically, without compromising the computation speed.

Reservoir computing has rekindled neuromorphic computing in photonics. One of the simplest technological implementations of reservoir computing consists of a semiconductor laser with delayed optical feedback. In this delay-based scheme, virtual nodes are distributed in time with a certain node distance and form a time-multiplexed network. The information processing performance of a semiconductor laser-based reservoir computing (RC) system is usually analysed by way of testing the laser-based reservoir computer on specific benchmark tasks. In this work, we will illustrate the optimal performance of the system on a chaotic time-series prediction benchmark. However, the goal is to analyse the reservoir’s performance in a task-independent way. This is done by calculating the computational capacity, a measure for the total number of independent calculations that the system can handle. We focus on the dependence of the computational capacity on the specifics of the masking procedure. We find that the computational capacity depends strongly on the virtual node distance with an optimal node spacing of 30 ps. In addition, we show that the computational capacity can be further increased by allowing for a well chosen mismatch between delay and input data sample time.

Delay-based reservoir computing is a neuromorphic computing technique employing a single nonlinear node, in this case a semiconductor laser subjected to a delayed optical self-feedback. This implementation of reservoir computing, while being versatile and highly performant, is limited in processing speed by the delay length. In an effort to reduce the required delay line length, while maintaining the same strong performance, we investigate if it is possible to distribute the processing power over more than one longitudinal mode. We therefore have numerically analyzed a rate equation model of a semiconductor laser with two longitudinal modes, delayed optical feedback and optical injection. Our modelling takes into account the carrier inversion moments that represent carrier gratings formed in the cavity during operation. This allows us to study the importance of modal interaction via carrier gratings and how this effects the computational power. We show that the setup with a dual-mode laser and an optimized reservoir parameter space, can reduce the delay-line fourfold in comparison with a single-mode laser setup.