Results 191 to 200 of about 517,396 (274)

Self-supervised and few-shot learning for robust bioaerosol monitoring. [PDF]

Aerobiologia (Bologna)
Willi A, Baumann P, Erb S, Gröger F, Zeder Y, Lionetti S.   +5 more
europepmc   +1 more source

Recent Advances and Challenges in Ammonia‐Hydrogen Energy Conversion

Advanced Science, EarlyView.
This work summarizes the latest progress of various catalytic methods in ammonia‐hydrogen energy conversion. The challenges and outlook of ammonia‐hydrogen energy conversion system are also emphasized. This work expects to build a blueprint of renewable and efficient ammonia‐hydrogen energy conversion systems under mild conditions.
Menghao Lv, Runchao Qin, Jianshuo Chen, Kaiwen Yang, Jianwei Lu, Weiwei Lei, Yifu Yu   +6 more
wiley   +1 more source

Few-shot learning for non-vitrified ice segmentation. [PDF]

Sci Rep
Vivas-Lago A, Castaño-Díez D.
europepmc   +1 more source

Organic Thin‐Film Transistors for Neuromorphic Computing

Advanced Electronic Materials, EarlyView.
Organic thin‐film transistors (OTFTs) are reviewed for neuromorphic computing applications, highlighting their power‐efficient, and biological time‐scale operation. This article surveys OFET and OECT devices, compares them with memristors and CMOS, analyzes how fabrication parameters shape spike‐based metrics, proposes standardized characterization ...
Luke McCarthy, Mohan V. Jacob, Mostafa Rahimi Azghadi   +2 more
wiley   +1 more source

Reproducing the Few-Shot Learning Capabilities of the Visual Ventral Pathway Using Vision Transformers and Neural Fields. [PDF]

Brain Sci
Su J, Xing L, Li T, Xiang N, Shi J, Jin D.   +5 more
europepmc   +1 more source

Emerging Memory and Device Technologies for Hardware‐Accelerated Model Training and Inference

Advanced Electronic Materials, EarlyView.
This review investigates the suitability of various emerging memory technologies as compute‐in‐memory hardware for artificial intelligence (AI) applications. Distinct requirements for training‐ and inference‐centric computing are discussed, spanning device physics, materials, and system integration.
Yoonho Cho, Dae‐won Kim, Yujin Kim, Jung‐Heum Na, Yuwon Jeong, Dong‐Yeop Lee, Shinhyun Choi   +6 more
wiley   +1 more source

Efficient In‐Hardware Matrix–Vector Multiplication and Addition Exploiting Bilinearity of Schottky Barrier Transistors Processed on Industrial FDSOI

Advanced Electronic Materials, EarlyView.
ABSTRACT Machine learning and Artificial Intelligence (AI) tasks have stretched traditional hardware to its limits. In‐hardware computation is a novel approach that aims to run complex operations, such as matrix–vector multiplication, directly at the device level for increased efficiency.
Juan P. Martinez, Niladri Bhattacharjee, Yuxuan He, Giulio Galderisi, Brojogopal Sapui, Sara Mannaa, Ian O'Connor, Violetta Sessi, Peter Javorka, Thomas Mikolajick, Jens Trommer   +10 more
wiley   +1 more source

Exploration of 3D Few-Shot Learning Techniques for Classification of Knee Joint Injuries on MR Images. [PDF]

Diagnostics (Basel)
Dang VH, Nguyen MT, Le NH, Nguyen TP, Tran QV, Mai TH, Vy VPT, Hung TNK, Lee CY, Tseng CL, Le NQK, Nguyen PA.   +11 more
europepmc   +1 more source

Safety of Sodium‐Ion Batteries: Evaluation and Perspective from Component Materials to Cells, Modules, and Packs

Advanced Energy Materials, EarlyView.
This review provides a bottom‐up evaluation of sodium‐ion battery safety, linking material degradation mechanisms, cell engineering parameters, and module/pack assembly. It emphasizes that understanding intrinsic material stability and establishing coordinated engineering control across hierarchical levels are vital for preventing degradation coupling ...
Won‐Gwang Lim, Seoa Kim, Erik A. Wu, Darren H. S. Tan, Shawn Peng, Xiaolin Li   +5 more
wiley   +1 more source

Few shot learning for phenotype-driven diagnosis of patients with rare genetic diseases. [PDF]

NPJ Digit Med
Alsentzer E, Li MM, Kobren SN, Noori A, Undiagnosed Diseases Network, Kohane IS, Zitnik M.   +6 more
europepmc   +1 more source