Results 101 to 110 of about 58,776 (261)

Electrically Coded Retinomorphic Spectrophotodetector

Advanced Materials, EarlyView.
Self‐powered retinomorphic pyro‐photodetector is demonstrated that avoids machine‐learning post‐processing and covers 365–940 nm. Electrostatic balancing of built‐in potential produces an electrical wavelength code, delivering <3 nm wavelength decoding accuracy with ∼46 µs response.
Mohit Kumar, Hyunmin Dang, Hyungtak Seo
wiley   +1 more source

Incremental Learning in Inductive Programming [PDF]

, 2010
Inductive programming systems characteristically exhibit an exponential explosion in search time as one increases the size of the programs to be generated. As a way of overcoming this, we introduce incremental learning, a process in which an inductive programming system automatically modifies its inductive bias towards some domain through solving a ...
openaire   +1 more source

Understanding Operando Water Management in Hydroxide‐Exchange‐Membrane Fuel Cells

Advanced Materials Interfaces, EarlyView.
Effective water management is vital for high‐performance hydroxide‐exchange‐membrane fuel cells. Using a custom water‐flux station, this study quantifies how membrane thickness, microporous layers, and operating conditions dictate internal water transport.
Catherine M. Weiss, Shiyi Wang, Brian P. Setzler, Yushan Yan, Adam Z. Weber   +4 more
wiley   +1 more source

A Hybrid Computational Framework for PCF‐based SPR Sensor With Machine Learning and xAI

Advanced Materials Interfaces, EarlyView.
A photonic crystal fiber‐based surface plasmon resonance (SPR) sensor integrating rectangular air holes along with conventional circular air holes achieves exceptional wavelength sensitivity of 15,000 nm/RIU across a broad refractive index range of 1.31–1.39. Integrated machine learning with explainable AI (xAI) models achieves high prediction accuracy
Mahabur Rahman Fahim, Sudeep Paul, Musrat Jahan, Md Abu Shahid Chowdhury   +3 more
wiley   +1 more source

Class-Incremental Learning: A Survey

IEEE Transactions on Pattern Analysis and Machine Intelligence
Deep models, e.g., CNNs and Vision Transformers, have achieved impressive achievements in many vision tasks in the closed world. However, novel classes emerge from time to time in our ever-changing world, requiring a learning system to acquire new knowledge continually.
Da-Wei Zhou 0001, Qi-Wei Wang, Zhi-Hong Qi, Han-Jia Ye, De-Chuan Zhan, Ziwei Liu 0002   +5 more
openaire   +3 more sources

Characterization of Droplet Formation in Ultrasonic Spray Coating: Influence of Ink Formulation Using Phase Doppler Anemometry and Machine Learning

Advanced Materials Technologies, EarlyView.
This study explores how machine learning models, trained on small experimental datasets obtained via Phase Doppler Anemometry (PDA), can accurately predict droplet size (D32) in ultrasonic spray coating (USSC). By capturing the influence of ink complexity (solvent, polymer, nanoparticles), power, and flow rate, the model enables precise droplet control
Pieter Verding, Danny E. P. Vanpoucke, Yunus T. Aksoy, Tobias Corthouts, Maria R. Vetrano, Wim Deferme   +5 more
wiley   +1 more source

Incremental Object Keypoint Learning

2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
Existing progress in object keypoint estimation primarily benefits from the conventional supervised learning paradigm based on numerous data labeled with pre-defined keypoints. However, these well-trained models can hardly detect the undefined new keypoints in test time, which largely hinders their feasibility for diverse downstream tasks.
Mingfu Liang, Jiahuan Zhou, Xu Zou 0002, Ying Wu 0001   +3 more
openaire   +2 more sources

3D Printing of Stretchable, Compressible and Conductive Porous Polyurethane for Soft Robotics

Advanced Materials Technologies, EarlyView.
A 3D‐printable porous dopamine‐polyurethane acrylate elastomer results in conductive, stretchable, and compressible structures that can be metallized in situ through catechol‐mediated silver reduction. The resulting material function as both compliant soft robot with a and strain sensors without complex assemblies, enabling fully 3D‐printed soft ...
Ouriel Bliah, Konstantin Sakharov, Pooi See Lee, Shlomo Magdassi   +3 more
wiley   +1 more source

Hierarchical Multi‐Material Architectures With Gradient Design for Dynamic‐Range Flexible Tactile Sensing

Advanced Materials Technologies, EarlyView.
Hierarchical multi‐material TPMS lattices are engineered as flexible tactile sensors by combining soft and stiff elastomeric layers with a conformal conductive coating. The bilayer architecture delivers sensitivity at low pressures while maintaining a broad detectable range under large loads, enabling reliable pressure and vibration monitoring for ...
Reza Noroozi, Domenic Quiquero, Yan Yan Shery Huang, HaoTian Harvey Shi   +3 more
wiley   +1 more source

Learning with incremental iterative regularization

, 2014
Within a statistical learning setting, we propose and study an iterative regularization algorithm for least squares defined by an incremental gradient method. In particular, we show that, if all other parameters are fixed a priori, the number of passes over the data (epochs) acts as a regularization parameter, and prove strong universal consistency, i ...
Lorenzo Rosasco, Silvia Villa
openaire   +5 more sources