arXiv:2607. 27844v1 Announce Type: cross Abstract: Physical computing leverages complex dynamical systems for energy-efficient data processing.
arXiv:2607. 00286v1 Announce Type: cross Abstract: Oscillatory neural networks (ONNs) have emerged as a promising neuromorphic architecture, leveraging coupled dynamical systems to perform computation and represent information through phase relationships.
Physics-informed neural networks (PINNs) are applied to model ion‑electronic drift‑diffusion in Pt/SrTiO₃/Si memristive heterostructures, overcoming numerical stiffness and multiscale spatial challenges. A cascaded PINN architecture with a custom Chebyshev spectral optimizer (DSO V2 Hybrid) isolates potential, carrier density, and vacancy transport into four sequential sub‑networks, avoiding condition numbers above 10¹⁶. The surrogate reproduces experimental conductive‑AFM current‑voltage hysteresis with R² > 0.96, maintains Poisson consistency, and offers differentiable inverse parameter estimation and linear‑time inference compared to conventional finite‑element solvers.
The paper introduces Competitive Dimerization Networks (CDNs) as a chemical learning framework where molecular species bind reversibly to form dimers, with binding affinities acting as tunable synaptic weights. Through a directed evolution protocol involving mutation, selection, and amplification of DNA-based components, CDNs can be trained in vitro to perform complex tasks such as multiclass classification, achieving strong output contrast and high mutual information. Comparative studies with in silico gradient descent show closely correlated performance, positioning CDNs as a promising platform for analog physical computation that bridges synthetic biology and machine learning.
arXiv:2609.22775v1 Announce Type: new Abstract: Spiking Neural Networks (SNNs) offer a promising path toward ultra-low-power artificial intelligence inference by emulating the event-driven computatio...
The paper develops a multiscale framework linking plasma deposition conditions to the functionality of sputtered SiO$_x$/Cu/SiO$_x$ memristive devices. By analyzing over 50,000 devices and combining plasma and atomistic simulations, it shows that device behavior arises from a probabilistic cascade of defect formation, evolution, and functional regime emergence, rather than deterministic mappings. A latent descriptor based on reconstructed oxygen‑vacancy density captures the combined effects of structural disorder and defect topology, linking hidden material properties to observable electrical responses and explaining variability in large‑area devices.
arXiv:2607. 02608v1 Announce Type: cross Abstract: Lightweight neuromorphic computing offers a promising route to efficient AI, with particular benefits for resource-constrained edge deployments.
arXiv:2607. 24396v1 Announce Type: cross Abstract: In deep learning, efficiency gets more and more important to compensate for the ongoing growth in model sizes and applications.
arXiv:2602. 07518v3 Announce Type: replace-cross Abstract: Kolmogorov-Arnold Networks (KANs) shift neural computation from linear layers to learnable nonlinear edge functions, but implementing these nonlinearities efficiently in hardware remains an open challenge.
arXiv:2606. 24075v1 Announce Type: cross Abstract: Although deep learning-based methods can achieve high accuracy in automatic modulation recognition (AMR) tasks, their high computational cost makes it difficult to strike a balance between accuracy and power consumption, thereby limiting their application on resource-constrained platforms.
arXiv:2608. 14734v1 Announce Type: cross Abstract: Deep learning models of nanocrystal synthesis enable the prediction of size and shape by encoding precursors and reaction conditions.
arXiv:2608. 08317v1 Announce Type: new Abstract: Biological neural systems achieve high efficiency and robustness through compartmentalized architectures.
arXiv:2606. 23742v1 Announce Type: cross Abstract: Physical neural networks promise low-power machine learning by computing directly with analogue device physics, but most architectures force nonlinear device responses to act as scalar weights.