Results 211 to 220 of about 72,703 (318)

Automatic Infant Movement Assessment Using Pose-LBP Features and a Cost-Sensitive Subspace kNN Ensemble. [PDF]

Bioengineering (Basel)
Ari A, Atalan Efkere P, Çangur EY, Uzun Akkaya K, Gurler Ari B, Elbasan B, Sengur A, Tian Y.   +7 more
europepmc   +1 more source

Vertical Deformation Mapping: Steering Optimiser Toward Flat Minima

CAAI Transactions on Intelligence Technology, EarlyView.
ABSTRACT Standard deep learning optimisation is typically conducted on shape‐fixed loss surfaces. However, shape‐fixed loss surfaces may impede optimisers from reaching flat regions closely associated with strong generalisation. In this work, we propose a new paradigm named deformation mapping to deform the loss surface during optimisation.
Liangming Chen, Longbang Wang, Man‐Fai Leung, Jianfeng Li, Long Jin   +4 more
wiley   +1 more source

Pairing particles into holonomies. [PDF]

Sci Adv
Neef V, Heinrich M, Wolterink TAW, Szameit A.   +3 more
europepmc   +1 more source

Two Subspaces [PDF]

Transactions of the American Mathematical Society, 1969
openaire   +1 more source

M3LoRA: Flexible Task Adaptation via Multiple Low‐Rank Matrices With Mixture‐of‐Subspaces and Minor Singular Components Initialization

CAAI Transactions on Intelligence Technology, EarlyView.
ABSTRACT Parameter‐efficient fine‐tuning (PEFT) has become a crucial paradigm for domain adaptation, achieving strong performance by updating only a small fraction of model parameters. Among various PEFT methods, low‐rank adaptation (LoRA) is widely adopted due to its structural simplicity and computational efficiency.
Xu Luo, Yongbin Liu, Chunping Ouyang, Ying Yu, Yang Yang   +4 more
wiley   +1 more source

A user centric group authentication scheme for secure communication. [PDF]

Sci Rep
Gerenli O, Karabulut-Kurt G, Ozdemir E.
europepmc   +1 more source

Multiple Transformer‐Based Models for Phase‐Sensitive Masking‐Based Single‐Channel Speech Enhancement

CAAI Transactions on Intelligence Technology, EarlyView.
ABSTRACT Leveraging both global contextual dependencies and local temporal‐spectral patterns can further enhance speech quality and intelligibility, motivating the integration of diverse neural network structures for improved mask estimation. Furthermore, due to the limitations of existing time‐frequency phase‐aware masks, a new constrained phase ...
Matin Pashaian, Sanaz Seyedin
wiley   +1 more source

Flexible neural representations of abstract structural knowledge in the human entorhinal cortex. [PDF]

Elife
Mark S, Schwartenbeck P, Hahamy A, Samborska V, Baram AB, Behrens TE.   +5 more
europepmc   +1 more source

An Efficient Method for Transient Temperature Calculation in Oil Natural Transformers Based on the Time‐Space Proper Orthogonal Decomposition

High Voltage, EarlyView.
ABSTRACT A reduced‐order model (ROM) for the temperature field based on time‐space proper orthogonal decomposition (POD) is presented to improve the computational efficiency of transient temperature rise in oil‐immersed power transformers with a complete oil natural convection cooling loop.
Haijuan Lan, Wenhu Tang, Zeyi Zhang, Jiahao Gong, Xiongwen Xu, Goran Strbac   +5 more
wiley   +1 more source

Random subspace-based ensemble classifier for high-dimensional data Using SPARK. [PDF]

PLoS One
Bhimineni VC, Senapati R.
europepmc   +1 more source