English
Related papers

Related papers: Understanding Task Performance of Time-Multiplexed…

200 papers

The combination of machine learning and quantum computing has emerged as a promising approach for addressing previously untenable problems. Reservoir computing is an efficient learning paradigm that utilizes nonlinear dynamical systems for…

Quantum Physics · Physics 2020-08-26 Jiayin Chen , Hendra I. Nurdin , Naoki Yamamoto

This paper introduces a novel framework for image and video demoir\'eing by integrating Maximum A Posteriori (MAP) estimation with advanced deep learning techniques. Demoir\'eing addresses inherently nonlinear degradation processes, which…

Computer Vision and Pattern Recognition · Computer Science 2025-06-23 Liangyan Li , Yimo Ning , Kevin Le , Wei Dong , Yunzhe Li , Jun Chen , Xiaohong Liu

Time delay reservoir computing (TDRC) using semiconductor lasers (SLs) has proven to be a promising photonic analog approach for information processing. One appealing property is that SLs subject to delayed optical feedback and external…

Signal Processing · Electrical Eng. & Systems 2023-05-10 Irene Estebanez , Apostolos Argyris , Ingo Fischer

Multifunctionality is a well observed phenomenological feature of biological neural networks and considered to be of fundamental importance to the survival of certain species over time. These multifunctional neural networks are capable of…

Neural and Evolutionary Computing · Computer Science 2021-02-03 Andrew Flynn , Vassilios A. Tsachouridis , Andreas Amann

Reservoir computing is a bio-inspired machine learning paradigm that exploits the intrinsic dynamics of nonlinear systems with fading memory for efficient temporal information processing. Microelectromechanical resonators offer a promising…

A delayed feedback reservoir (DFR) is a type of reservoir computing system well-suited for hardware implementations owing to its simple structure. Most existing DFR implementations use analog circuits that require both digital-to-analog and…

Hardware Architecture · Computer Science 2023-07-24 Sosei Ikeda , Hiromitsu Awano , Takashi Sato

Reservoir computing is a popular approach to design recurrent neural networks, due to its training simplicity and approximation performance. The recurrent part of these networks is not trained (e.g., via gradient descent), making them…

Neural and Evolutionary Computing · Computer Science 2021-02-15 Pietro Verzelli , Cesare Alippi , Lorenzo Livi , Peter Tino

This paper presents a stochastic logic time delay reservoir design. The reservoir is analyzed using a number of metrics, such as kernel quality, generalization rank, performance on simple benchmarks, and is also compared to a deterministic…

Machine Learning · Statistics 2017-02-15 Cory Merkel

Modern machine learning models use an ever-increasing number of parameters to train (175 billion parameters for GPT-3) with large datasets to obtain better performance. Bigger is better has been the norm. Optical computing has been…

Mapping applications onto heterogeneous platforms is a difficult challenge, even for simple application patterns such as pipeline graphs. The problem is even more complex when processors are subject to failure during the execution of the…

Distributed, Parallel, and Cluster Computing · Computer Science 2008-03-26 Anne Benoit , Veronika Rehn-Sonigo , Yves Robert

Advances in artificial intelligence are driven by technologies inspired by the brain, but these technologies are orders of magnitude less powerful and energy efficient than biological systems. Inspired by the nonlinear dynamics of neural…

Optical kernel machines offer high throughput and low latency. A nonlinear optical kernel can handle complex nonlinear data, but power consumption is typically high with the conventional nonlinear optical approach. To overcome this issue,…

Optics · Physics 2025-11-25 SeungYun Han , Fei Xia , Sylvain Gigan , Bruno Loureiro , Hui Cao

We investigate the computational power of passive and active linear optical elements and photo-detectors. We show that single photon sources, passive linear optics and photo-detectors are sufficient for implementing reliable quantum…

Quantum Physics · Physics 2007-05-23 E. Knill , R. Laflamme , G. Milburn

Reservoir computing is an emerging, but very successful approach towards processing and classification of various signals. It can be described as a model of a transient computation, where influence of input changes internal dynamics of…

We consider the modeling, stability analysis and controller design problems for discrete-time LTI systems with state feedback, when the actuation signal is subject to switching propagation delays, due to e.g. the routing in a multi-hop…

Optimization and Control · Mathematics 2014-01-09 R. M. Jungers , A. D'Innocenzo , M. D. Di Benedetto

The dissipativity framework is widely used to analyze stability and performance of nonlinear systems. By embedding nonlinear systems in an LPV representation, the convex tools of the LPV framework can be applied to nonlinear systems for…

Systems and Control · Electrical Eng. & Systems 2021-09-21 Patrick J. W. Koelewijn , Roland Tóth

We propose the use of weakly nonlinear passive materials for prospective applications in integrated quantum photonics. It is shown that strong enhancement of native optical nonlinearities by electromagnetic field confinement in photonic…

Mesoscale and Nanoscale Physics · Physics 2015-06-12 S. Ferretti , V. Savona , D. Gerace

Photonic delay systems have revolutionized the hardware implementation of Recurrent Neural Networks and Reservoir Computing in particular. The fundamental principles of Reservoir Computing strongly benefit a realization in such complex…

Emerging Technologies · Computer Science 2021-11-08 D. Brunner , B. Penkovsky , B. A. Marquez , M. Jaquot , I. Fischer , L. Larger

Linear attention significantly reduces the computational complexity of Transformers from quadratic to linear, yet it consistently lags behind softmax-based attention in performance. We identify the root cause of this degradation as the…

Machine Learning · Computer Science 2026-02-05 Weikang Meng , Liangyu Huo , Yadan Luo , Yaowei Wang , Yingjian Li , Zheng Zhang

Introduction. Reservoir computing is a growing paradigm for simplified training of recurrent neural networks, with a high potential for hardware implementations. Numerous experiments in optics and electronics yield comparable performance to…

Neural and Evolutionary Computing · Computer Science 2020-04-07 Piotr Antonik , Nicolas Marsal , Daniel Brunner , Damien Rontani