Related papers: Reinforcement Learning in a large scale photonic R…

Data inconsistency leads to a slow training process when deep neural networks are used for the inverse design of photonic devices, an issue that arises from the fundamental property of non-uniqueness in all inverse scattering problems. Here…

The effectiveness of recurrent neural networks can be largely influenced by their ability to store into their dynamical memory information extracted from input sequences at different frequencies and timescales. Such a feature can be…

Analog neuromorphic photonic processors are uniquely positioned to harness the ultrafast bandwidth and inherent parallelism of light, enabling scalability, on-chip integration and significant improvement in computational performance.…

Photonic reservoir computing (PRC) is a special hardware recurrent neural network, which is featured with fast training speed and low training cost. This work shows a wavelength-multiplexing PRC architecture, taking advantage of the…

Deep neural networks (DNNs) have substantial computational requirements, which greatly limit their performance in resource-constrained environments. Recently, there are increasing efforts on optical neural networks and optical computing…

Residual neural networks (ResNets) are a promising class of deep neural networks that have shown excellent performance for a number of learning tasks, e.g., image classification and recognition. Mathematically, ResNet architectures can be…

In photonic neural network a key building block is the perceptron. Here, we describe and demonstrate a complex-valued photonic perceptron that combines time and space multiplexing in a fully passive silicon photonics integrated circuit. An…

Computational imaging systems jointly design computation and hardware to retrieve information which is not traditionally accessible with standard imaging systems. Recently, critical aspects such as experimental design and image priors are…

Photonic neuromorphic computing offers compelling advantages in power efficiency and parallel processing, but often falls short in realizing scalable nonlinearity and long-term memory. We overcome these limitations by employing silicon…

Plastic self-adaptation, nonlinear recurrent dynamics and multi-scale memory are desired features in hardware implementations of neural networks, because they enable them to learn, adapt and process information similarly to the way…

Deep neural networks have shown superior performance in many regimes to remember familiar patterns with large amounts of data. However, the standard supervised deep learning paradigm is still limited when facing the need to learn new…

Recent years have witnessed the great success of convolutional neural network (CNN) based models in the field of computer vision. CNN is able to learn hierarchically abstracted features from images in an end-to-end training manner. However,…

Traditional neural networks require enormous amounts of data to build their complex mappings during a slow training procedure that hinders their abilities for relearning and adapting to new data. Memory-augmented neural networks enhance…

Feedback-driven recurrent spiking neural networks (RSNNs) are powerful computational models that can mimic dynamical systems. However, the presence of a feedback loop from the readout to the recurrent layer de-stabilizes the learning…

Deep neural networks usually process information through multiple hidden layers. However, most hardware reservoir computing recurrent networks only have one hidden reservoir layer, which significantly limits the capability of solving…

In recent years, deep neural networks (DNN) have demonstrated significant business impact in large scale analysis and classification tasks such as speech recognition, visual object detection, pattern extraction, etc. Training of large DNNs,…

Deep Reinforcement Learning has enabled the learning of policies for complex tasks in partially observable environments, without explicitly learning the underlying model of the tasks. While such model-free methods achieve considerable…

We present a deep photonic neural network architecture based on ultrafast binary optical modulation from a digital micro-mirror device (DMD), optical scattering in random medium, high-speed photodetection with a CMOS sensor, and…

Artificial neural networks have advanced the frontiers of reversible steganography. The core strength of neural networks is the ability to render accurate predictions for a bewildering variety of data. Residual modulation is recognised as…

Reinforcement learning (RL) is a foundation of learning in biological systems and provides a framework to address numerous challenges with real-world artificial intelligence applications. Efficient implementations of RL techniques could…