Reconfigurable Silicon Photonics Extreme Learning Machine with Random Non-linearities as Neural Processor and Physical Unclonable Function

An alternative extreme learning machine -ELM- paradigm is presented exploiting random non-linearities -RN, named RN-ELM, instead of a conventional fixed node non-linearity. This method is implemented on a hybrid neural engine, with the physical layer realized by an integrated silicon photonic mesh and the digital layer by a simple regression algorithm. Non-linearities are intrinsically non-power depended and are generated through non-linear frequency to power mapping offered by optical filters. The numerical evaluation is based on an experimentally derived transfer function of an all-pass filter, implemented on a silicon reconfigurable photonic integrated chip -RPIC. RN-ELM is evaluated in a twofold manner; first as a machine learning scheme, where the expressivity offered by multiple, yet random, activation functions lead to a compact and highly simplified design with 5 optical filters, offering state-of-the-art performance in time-series prediction tasks with minimum hardware requirements. The second scenario entails its deployment as a physical unclonable function -PUF, for authentication applications directly in the physical layer. In this case, the random activation functions are associated with unavoidable, fabrication related waveguide imperfections that can act as hardware signatures. Numerical results reveal a probability of cloning as low as 10e-15, which corresponds to a highly secure authentication token.

Photonic Neuromorphic Accelerators for Event-Based Imaging Flow Cytometry

In this work, we present experimental results of a high-speed label-free imaging cytometry system that seamlessly merges the high-capturing rate and data sparsity of an event-based CMOS camera with lightweight photonic neuromorphic processing. This combination offers high classification accuracy and a massive reduction in the number of trainable parameters of the digital machine-learning back-end. The photonic neuromorphic accelerator is based on a hardware-friendly passive optical spectrum slicing technique that is able to extract meaningful features from the generated spike-trains. The experimental scenario comprises the discrimination of artificial polymethyl methacrylate calibrated beads, having different diameters, flowing at a mean speed of 0.01m/sec. Classification accuracy, using only lightweight, digital machine-learning schemes has topped at 98.2%. On the other hand, by experimentally pre-processing the raw spike data through the proposed photonic neuromorphic spectrum slicer we achieved an accuracy of 98.6%. This performance was accompanied by a reduction in the number of trainable parameters at the classification back-end by a factor ranging from 8 to 22, depending on the configuration of the digital neural network.

All-Optical, Reconfigurable and Power Independent Neural Activation Function by Means of Phase Modulation

In this work, we present numerical results concerning an integrated photonic non-linear activation function that relies on a power independent, non-linear phase to amplitude conversion in a passive optical resonator. The underlying mechanism is universal to all optical filters, whereas here, simulations were based on micro-ring resonators (MRRs). Investigation revealed that the photonic neural node can be tuned to support a wide variety of continuous activation functions that are relevant to the neural network architectures, such as the sigmoid and the softplus functions. The proposed photonic node is numerically evaluated in the context of time delayed reservoir computing (TDRC) scheme, targeting the one-step ahead prediction of the Santa Fe series. The proposed phase to amplitude TDRC is benchmarked versus the conventional amplitude based TDRC, showcasing a performance boost by one order of magnitude.

Integrated Photonic Accelerator Based on Optical Spectrum Slicing for Convolutional Neural Networks

In this work we numerically analyze a passive photonic integrated neuromorphic accelerator based on hardware-friendly optical spectrum slicing nodes. The proposed scheme can act as a fully analogue convolutional layer, preprocessing information directly in the optical domain. The proposed scheme allows the extraction of meaningful spatio-temporal features from the incoming data, thus when used prior to a simple fully connected digital single layer network it can boost performance with negligible power consumption. Numerical simulations using the MNIST dataset confirmed the acceleration properties of the proposed scheme, where 10 neuromorphic nodes can replace the convolutional layers of a sophisticated LeNet-5 network, thus reducing the number of total floating point operations per second (FLOPS) by 98% while offering a 97.2% classification accuracy.