Tensor analytics lays the mathematical basis for the prosperous promotion of multiway signal processing. To increase computing throughput, mainstream processors transform tensor convolutions into matrix multiplications to enhance the parallelism of computing. However, such order-reducing transformation produces data duplicates and consumes additional memory. Here, we propose an integrated photonic tensor flow processor (PTFP) without digitally duplicating the input data. It outputs the convolved tensor as the input tensor ‘flows’ through the processor. The hybrid manipulation of optical wavelengths, space dimensions, and time delay steps, enables the direct representation and processing of high-order tensors in the optical domain. In the proof-of-concept experiment, an integrated processor manipulating wavelengths and delay steps is implemented for demonstrating the key functionalities of PTFP. The multi-channel images and videos are processed at the modulation rate of 20 Gbaud. A convolutional neural network for video action recognition is demonstrated on the processor, which achieves an accuracy of 97.9%.
Optical implementations of neural networks (ONNs) herald the next-generation high-speed and energy-efficient deep learning computing by harnessing the technical advantages of large bandwidth and high parallelism of optics. However, due to the problems of the incomplete numerical domain, limited hardware scale, or inadequate numerical accuracy, the majority of existing ONNs were studied for basic classification tasks. Given that regression is a fundamental form of deep learning and accounts for a large part of current artificial intelligence applications, it is necessary to master deep learning regression for further development and deployment of ONNs. Here, we demonstrate a silicon-based optical coherent dot-product chip (OCDC) capable of completing deep learning regression tasks. The OCDC adopts optical fields to carry out operations in the complete real-value domain instead of in only the positive domain. Via reusing, a single chip conducts matrix multiplications and convolutions in neural networks of any complexity. Also, hardware deviations are compensated via in-situ backpropagation control provided the simplicity of chip architecture. Therefore, the OCDC meets the requirements for sophisticated regression tasks and we successfully demonstrate a representative neural network, the AUTOMAP (a cutting-edge neural network model for image reconstruction). The quality of reconstructed images by the OCDC and a 32-bit digital computer is comparable. To the best of our knowledge, there is no precedent of performing such state-of-the-art regression tasks on ONN chips. It is anticipated that the OCDC can promote the novel accomplishment of ONNs in modern AI applications including autonomous driving, natural language processing, and scientific study.
Anthropomorphic grippers have grown considerably for decades and changed the landscape of the robotics field by offering robots with unprecedented adaptability and conformability to different shapes and sizes. [1][2][3] These grippers exploit the flexibility and deformability of materials to achieve compliance matching and biocompatibility without complex and precise control schemes. [4][5][6][7] Meanwhile, inheriting the nature of soft materials, they have been extensively employed in robotic applications in a compatible and interactive way, e.g., serve as grippers to grasp fragile targets, [8] or robotic hands for artificial limbs. [9] However, most soft grippers still have limitations in the coordination of high compliance and variable stiffness for safely operating delicate and fragile objects. [10][11][12] The impressive adaptability and manipulation capability of creature structures have led to a host of bioinspired solutions. [13][14][15] To mimic the grasping characteristics of creatures, extensive studies focus on variable stiffness mechanisms by developing stiffness-tunable materials and morphable structures for robotic systems. [16,17] These efforts mainly involve shape-memory materials, [18][19][20] rheological materials, [21] elastomers with electroactive liquids, [22,23] and granular or laminar jamming. [24][25][26][27][28] They can be utilized to modulate the local or global stiffness by adjusting the activation condition of the material or mechanical interactions of the structures. [29,30] Combining these variable stiffness methods, the grippers can adapt to the objects and complete the tasks that require strength. [31,32] Nevertheless, despite the impressive contribution of these efforts to improve the performance of grippers, they generally suffer from poor repeatability, slow response, and intricate control. [33][34][35] Therefore, it remains a challenge to regulate stiffness actively in a manner of convenient fabrication, safe interaction, and high efficiency.Despite structural compliance to safely interact with the targets, most robotic grippers can only switch their configuration between straight and curved states.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.