Decision, Inference, and Information: Formal Equivalences Under Active Inference. [PDF]
Sweeney P, Ruiz-Serra J, Harré MS.
europepmc +1 more source
A Flexible and Energy‐Efficient Compute‐in‐Memory Accelerator for Kolmogorov–Arnold Networks
This article presents KA‐CIM, a compute‐in‐memory accelerator for Kolmogorov–Arnold Networks (KANs). It enables flexible and efficient computation of arbitrary nonlinear functions through cross‐layer co‐optimization from algorithm to device. KA‐CIM surpasses CPU, ASIC, VMM‐CIM, and prior KAN accelerators by 1–3 orders of magnitude in energy‐delay ...
Chirag Sudarshan +6 more
wiley +1 more source
Mathematical Modelling and Intuition in Microbiology: A Perspective. [PDF]
Lopez JA, Erez A.
europepmc +1 more source
Optimizing 3D Bin Packing of Heterogeneous Objects Using Continuous Transformations in SE(3)
This article presents a method for solving the three‐dimensional bin packing problem for heterogeneous objects using continuous rigid‐body transformations in SE(3). A heuristic optimization framework combines signed‐distance functions, neural network approximations, point‐cloud bin modeling, and physics simulation to ensure feasibility and stability ...
Michele Angelini, Marco Carricato
wiley +1 more source
Bayesian inference of RNA velocity incorporating timepoints, lineage bifurcations, and count data. [PDF]
Gu Y, Song Y, Blaauw D, Welch JD.
europepmc +1 more source
Four decades of retinal vessel segmentation research (1982–2025) are synthesized, spanning classical image processing, machine learning, and deep learning paradigms. A meta‐analysis of 428 studies establishes a unified taxonomy and highlights performance trends, generalization capabilities, and clinical relevance.
Avinash Bansal +6 more
wiley +1 more source
GWKBR: a novel method integrating machine learning and Bayesian inference framework to improve genomic prediction accuracy. [PDF]
Wang X, Jiang J, Zhang Z, Zhang Y.
europepmc +1 more source
This paper presents a high‐speed object pose estimation method that deconstructs objects into geometric components. Inspired by human cognitive generalization, it detects these primitives and infers the 6D pose from their stable spatial configuration.
Xuyang Li +6 more
wiley +1 more source
Methods for Setting Device Specifications for Analog In‐Memory Computing Inference
Non‐volatile memories (NVMs) are being developed for analog in‐memory computing for energy‐efficient, high‐speed deep learning inference. As technology is moving to industry adoption, a method to define required NVM specifications is critical for improving performance and reducing manufacturing cost.
Zhenyu Wu +3 more
wiley +1 more source
Life as Counterfactual Geometry: An Adversarial Theory of Biological Function. [PDF]
Buzea CG +7 more
europepmc +1 more source

