Neural Networks and Reservoir Computing

Últimos artículos

• Fractional State Space Transition for Long Sequence Modeling

  Ivan Kobyzev, Abbas Ghaddar, Ali Nasiri-Sarvi, Lifeng Shang, Yufei Cui · 1 de octubre de 2026

  State Space Models (SSMs) compress sequence history into a bounded recurrent state, making the resulting memory law a central architectural choice for long-context performance. Most modern SSMs rely on ODE-based dynamics that lead to exponential forgetting, limiting their ability to retain informati…

• Digital Twin Modeling of Quantum Dynamical Systems: Dissipative Quantum Reservoir Computing

  Abhijit Sen, Bikram Keshari Parida, Shital Chauhan, Mahima Arya, Denys I. Bondar · 30 de septiembre de 2026

  Modeling the response of driven many-body quantum systems from input--output data is difficult: the dynamics are nonlinear, history dependent, and expensive to simulate as system size grows. A paradigmatic case is High-Harmonic Generation~(HHG), where a strong field drives a medium to emit radiation…

• Beyond Quadratic Loss: The Stability Phase Diagram of Adam

  Gaoxiang Tang, Huanran Chen, Ziming Liu · 28 de septiembre de 2026

  Loss spikes are recurrent instabilities in neural-network training and can arise from multiple mechanisms. For Adam in particular, macroscopic loss spikes have been linked to optimizer dynamics, yet how its two momentum timescales govern them remains unclear. We investigate this dependence by mappin…

• Task-Resolved Fisher Spectroscopy for Quantum Reservoir Computing

  Yang Peng · 25 de septiembre de 2026

  Quantum reservoir computing (QRC) uses fixed quantum dynamics to encode a time series and trains only a classical readout, but a benchmark capacity alone does not reveal whether task information is lost in the reservoir, the measurement, feature compression, or finite sampling. We introduce \emph{ta…

• Inference of Unknown Dynamical Components Using Next Generation Reservoir Computing: From Chaotic Systems to Climate Data

  Jule Budnick, Andrew Keane, Serhiy Yanchuk · 22 de septiembre de 2026

  We investigate next generation reservoir computing (NGRC) as a data-driven approach for inferring unseen components of dynamical systems. We compare NGRC with traditional reservoir computing (RC) using the Lorenz and R\"ossler system, where two unknown components are inferred from one given componen…

• Prediction of Nonlinear Oscillations in a Jumping Quarter-Car Model Using Reservoir Computing

  Masahisa Watanabe, Shiva Dixit, Nirmal Punetha, Swati Chauhan, Manish Dev Shirimali · 22 de septiembre de 2026

  Reliable prediction of vehicle dynamics is essential for smart driving applications such as autonomous control and advanced driver-assistance systems. Off-road vehicles used in agricultural and construction settings are particularly prone to nonlinear behavior, including bifurcations and chaotic mot…

• Feasibility and Memory Mechanisms of Chern-Simons Context Reservoir Computation

  Jyotiranjan Beuria, Venkatesh H. Chembrolu · 15 de septiembre de 2026

  We investigate whether a Chern-Simons (CS) context reservoir is a viable computational substrate and whether evolving its gauge connection provides a benefit beyond simpler mechanisms. The reservoir state is a density fluctuation on a two-dimensional context manifold, whose drift is generated by a d…

• LoRA-RC: Reservoir Computing with Low-Rank Adaptation

  Wenbin Wan · 14 de septiembre de 2026

  Reservoir computing (RC) trains only a linear readout over a fixed recurrent layer, making it fast and data-efficient for online prediction. However, a static reservoir degrades under system drift, readout-only adaptation is then insufficient, and unconstrained reservoir adaptation can destroy the e…

• Coherent Floquet quantum reservoirs for molecular property prediction

  Luofei Wang, Da Zhang, Congren Wang, Yiming Li, Yuxiao Yang, Xuan Zhang, Xuefeng Cui, Zhang-Qi Yin · 11 de septiembre de 2026

  Quantum reservoir computing (QRC) uses quantum dynamics to represent input histories for prediction through a trained classical readout. Discrete time crystals (DTCs) exhibit robust subharmonic responses under periodic driving, and previous work has used their dynamics to construct DTC-QRC. Here we …

• When Quantization Breaks Memory: Recurrent-State Write-Back in Low-Precision Temporal Inference

  Ismail Erbas, Xavier Intes, Vikas Pandey · 7 de septiembre de 2026

  Quantization is widely used to reduce the computational and memory demands of neural-network inference. In recurrent networks, however, the quantized state is stored and returned at the next time step, so the rule used to store that state can alter subsequent computations. Here, we introduce recurre…

• Prospective Coding Improves Learning in Deep Continuous-Time Recurrent Networks

  Shivang Rawat, Mirko Morello, Flaviano Morone, David J. Heeger · 4 de septiembre de 2026

  Temporal integration gives continuous-time recurrent networks memory, but in deep stacks it also delays bottom-up signals and attenuates top-down errors. We develop Recursive Quadrature Filters (RQFs), biologically motivated complex-valued temporal filters that are a special case of diagonal state-s…

• How Temporal Correlations Shape Memory in Linear Recurrent Neural Networks

  Arnol Manuel Fokam, Fasseu Sieyondji Akpevwoghene, Edem Fiifi Dawson · 2 de septiembre de 2026

  The linear recurrent neural network (LRNN) is a simple model for studying how much memory a network builds up as it trains. For uncorrelated inputs, earlier work found that training itself settles the network between keeping the past and reacting only to the present. Real sequences are correlated, a…

• Memristive-Friendly Hadamard Reservoir Computing: Structured, Multiplier-Free Recurrences at Scale

  Andrea Ceni, Gianluca Milano, Carlo Ricciardi, Claudio Gallicchio · 31 de agosto de 2026

  Reservoir Computing (RC) designs Recurrent Neural Networks around a fixed, i.e., untrained, recurrent layer, and is a natural candidate for neuromorphic hardware. Memristive-friendly reservoirs derive the neuron dynamics from memristive-device kinetics, but still rely on dense recurrent matrices, wh…

• Continuous Quantum Feedback Control via Kraus-Parameterized Belief Reinforcement Learning

  Priyanshi Singh, Krishna Bhatia · 18 de agosto de 2026

  Quantum feedback control requires acting on noisy continuous measurement records without direct access to the underlying quantum state. We propose Kraus-Parameterized Belief Reinforcement Learning, a pipeline in which a recurrent encoder, constrained to the Stiefel manifold, produces density-matrix …

• Unifying Physical Backpropagation

  Cyrill B\"osch, Yigithan Gediz, Hakan T\"ureci · 13 de agosto de 2026

  Physical computing systems exploit device dynamics for computation, but their gradient-based optimization is challenging: backpropagation through a digital twin suffers from model-reality gap. On-device gradient computation could resolve this issue, and a handful of theoretical and experimental stud…

• Cavity-Enhanced Collective Quantum Processing with Polarization-Encoded Qubits

  Kamil Wereszczy\'nski, J\'ozef Cyran, Adam Brzezowski, Dawid Za{\l}u\.zny, Robert Potoniec, Kasper Wi\'sniowski, Agnieszka Michalczuk · 13 de agosto de 2026

  We introduce a cavity-enhanced optical architecture for collective quantum processing in which logical qubits are encoded in the polarization subspace of recirculating intracavity modes. The physical carrier and computational degree of freedom are explicitly separated: harmonic cavity bundles provid…

• Ghost Features and Spooky Transfer Learning for Hypercomplex-Valued Neural Networks

  Guilherme Vieira Neto, Marcos Eduardo Valle · 11 de agosto de 2026

  Hypercomplex numbers extend the concept of complex numbers by introducing additional imaginary components. Besides increasing dimensionality, operations on the imaginary parts provide algebraic and geometrical properties that can be beneficial for solving machine learning problems. In this paper, we…

• Rethinking Reservoir Pruning: A Dynamical Perspective for Echo State Networks

  Sudip Laudari, Puspa Raj Adhikari · 6 de agosto de 2026

  Echo State Networks (ESNs) offer an efficient framework for temporal prediction, but their randomly initialized reservoirs are often over-parameterized and dynamically redundant. Existing pruning methods largely rely on static connectivity or activation statistics, which may overlook neurons that sh…

• Lindblad-Inspired Multi-Timescale Reservoir Computing with Separable Rotation and Dissipation

  Jyotiranjan Beuria, Amit Shukla · 6 de agosto de 2026

  Echo-state networks enable efficient temporal learning by fixing the recurrent dynamics and training only a linear readout. However, conventional reservoirs typically accommodate signal mixing, memory retention, and stability within a single random recurrent matrix. Existing structured designs impro…

• From Digital to Physical Reservoir Computing: Co-Optimizing Soft Robotic Reservoirs via Dynamics Matching

  Nicola Visentin, Maximilian St\"olzle, Mariano Ram\'irez Montero, Francesco Braghin, Daniela Rus, Cosimo Della Santina · 4 de agosto de 2026

  Soft robotic substrates are promising for Physical Reservoir Computing (PRC) because their compliant nonlinear dynamics can provide temporal memory, high-dimensional state transformations, and efficient inference. However, physical reservoirs are often adopted as-is rather than pretrained or co-opti…

• Belief-Contraction-Driven Active Inverse Source Localization and Characterization

  Yiwei Shi, Mengyue Yang, Qi Zhang, Cunjia Liu, Weinan Zhang, Weiru Liu · 4 de agosto de 2026

  Active inverse source localization and characterization (ISLC) in dynamic fields requires sequential decision making under partial observability, where a mobile sensor must infer latent source parameters from sparse, noisy readings. We introduce a belief-contraction-driven approach that unifies infe…

• From Pixels to PCells: A Neurosymbolic Approach to Photonic Component Creation

  Aadarsh Agarwal, Kenaish Al Qubaisi, Dirk Englund · 30 de julio de 2026

  We present PixCell, a neurosymbolic system in which multimodal agents convert a visually presented photonic component into a parametric program over a small domain-specific language (DSL) of geometric primitives. A system enabling deterministic visual verification renders evaluation asymmetrically c…

• Investigating reservoir computing for branch predictionin pipelined processors using emerging CMOS memristor devices

  Harvey Samuel George Johnson, Sendy Phang · 30 de julio de 2026

  This project aimed to develop a novel reservoir compute (RC) implementation framework targeting high-speed operation and integration with CMOS digital logic. With the target workload of branch prediction (BP) for multistage pipelined central pro-cessing unit (CPU) cores. For this, a novel memristor …

• Frequency-Based Reservoir computing

  Arthur S Powanwe · 28 de julio de 2026

  Reservoir computing has emerged as an efficient machine learning framework for predicting time series generated by dynamical systems. In contrast to other machine and deep learning approaches, a reservoir computing trains only the output layer via linear regression, leaving the reservoir (recurrent …

• When Every Simulation Counts: Value-Based Reinforcement Learning for Accelerated Photonics Inverse Design

  Longying Wen, Feiyang Wu, Jinglin Yu, Chongxian Yuan, Renjie Li, Zhaoyu Zhang · 28 de julio de 2026

  Photonic-crystal surface-emitting lasers (PCSELs) can combine high-power operation with narrow-divergence surface emission, but optimizing coupled parameters requires costly full-wave simulations. Deep Q-network (DQN) optimization can reuse simulated transitions to guide edits, yet which value-learn…