Ecoefficiency Analysis and Regression in Data Conversion for Spiking Neural Network Training
The environmental footprint of spiking neural networks is quantified during dataset encoding and training for autonomous driving regression across three benchmarks. Temporal depth emerges as the dominant driver of energy consumption and CO2 emissions, while the accuracy–energy trade‐off proves dataset‐dependent. On conventional hardware, spiking models
Fernando S. Martínez +3 more
wiley +1 more source
What is so hard about abstract words, anyways? A neuromechanistic explanation using brain-constrained neural network models. [PDF]
Dobler FR, Stroppa L, Pulvermüller F.
europepmc +1 more source
Comparative Analysis of Model‐Agnostic Explanation Methods in Materials Science
To address the critical lack of explainable artificial intelligence (XAI) benchmarks in materials science, we present a quantitative and qualitative analysis of six XAI methods applied to molecular fingerprints. Our results reveal significant discrepancies in feature importance rankings, demonstrating that the chosen explanation approach introduces ...
Anna Przybyłowska +7 more
wiley +1 more source
Extending standardized speech analysis across languages: An Italian toolkit for transcription and coding of neurological speech. [PDF]
Benzini A +5 more
europepmc +1 more source
A Scalable and Resource‐Efficient Pipelined p‐Computer for Probabilistic Ising Machines
(a) Block diagram of the portfolio optimization problem: given M assets, the goal is to determine the optimal weights w that maximize the expected return (based on the mean historical assets return u), while minimizing the risk, quantified by the assets covariance matrix S.
Deborah Volpe +9 more
wiley +1 more source
The Changing Paradigm of Neuroinflammation in Epilepsy: A Bibliometric Analysis from Microglial Activation to Gut-Brain Axis. [PDF]
Jiang J, Gong X, Zou Y, Fan H.
europepmc +1 more source
Hardware‐learning co‐design combines volar‐plate‐inspired passive‐joint constraints with mechanism‐aware reinforcement learning for a low‐cost parallel‐linkage gripper. The resulting system performs quasi‐static object adjustment and dynamic pinch grasping, demonstrating reliable planar in‐hand manipulation and successful sim‐to‐real transfer. Parallel
Yanzhou Jin +4 more
wiley +1 more source
Procedural or declarative deficit in adults with developmental dyslexia? A study of Artificial grammar learning. [PDF]
Nardacchione G +2 more
europepmc +1 more source
AI‐Based Immortality: The Ethical Advantage of the Aretai Approach
ABSTRACT The convergence of artificial intelligence, digital identity technologies, and biogerontological ambitions has produced a novel set of philosophical problems that have not yet been adequately addressed within mainstream bioethical discourse. Digital life extension—encompassing AI‐generated avatars, neural data preservation, mind uploading, and
Mirko Daniel Garasic
wiley +1 more source
Abstract This study examines the impact of soil erosion on agricultural land values in the United States (US) Midwest. Based on a novel county‐level panel data set with information on soil erosion levels and agricultural land values covering five census years (1997, 2002, 2007, 2012, and 2017), we separately investigate the direct effect of two types ...
Le Chen +3 more
wiley +1 more source

