Results 31 to 40 of about 98,022 (269)
A Comparative Study on Regularization Strategies for Embedding-based Neural Networks
, 2015 This paper aims to compare different regularization strategies to address a common phenomenon, severe overfitting, in embedding-based neural networks for NLP. We chose two widely studied neural models and tasks as our testbed. We tried several frequently
Chen, Yunchuan +5 more
core +1 more source
Use of Augmentation Data and Hyperparameter Tuning in Batik Type Classification using the CNN Model
Sistemasi: Jurnal Sistem InformasiBatik is one of Indonesia's most recognized artistic cultures in the world and has different motifs and types of traditional batik and each has its own uniqueness.
Siti Auliaddina, Toni Arifin
doaj +1 more source
Is One Hyperparameter Optimizer Enough?
, 2018 Hyperparameter tuning is the black art of automatically finding a good combination of control parameters for a data miner. While widely applied in empirical Software Engineering, there has not been much discussion on which hyperparameter tuner is best ...
Bergstra J. +3 more
core +1 more source
Advanced Engineering Materials, EarlyView.Predicting extreme defects in additive manufacturing remains a key challenge limiting its structural reliability. This study proposes a statistical framework that integrates Extreme Value Theory with advanced process indicators to explore defect–process relationships and improve the estimation of critical defect sizes. The approach provides a basis for
Muhammad Muteeb Butt +8 more
wiley +1 more source
Artificial Intelligence in GeosciencesMachine learning (ML) algorithms are frequently used in landslide susceptibility modeling. Different data handling strategies may generate variations in landslide susceptibility modeling, even when using the same ML algorithm.
Guruh Samodra +2 more
doaj +1 more source
Additive Gaussian Process Regression for Predictive Design of High‐Performance, Printable Silicones
Advanced Engineering Materials, EarlyView.A chemistry‐aware design framework for tuning printable polydimethylsiloxane (PDMS) for vat photopolymerization (VPP) is developed using additive Gaussian process (GP) modeling. Polymer network mechanics informs variable groupings, feasible formulation constraints, and interaction variables.
Roxana Carbonell +3 more
wiley +1 more source
Lipschitz Adaptivity with Multiple Learning Rates in Online Learning [PDF]
, 2019 We aim to design adaptive online learning algorithms that take advantage of any special structure that might be present in the learning task at hand, with as little manual tuning by the user as possible. A fundamental obstacle that comes up in the design
Koolen, Wouter M. +2 more
core +1 more source
Multimodal Data‐Driven Microstructure Characterization
Advanced Engineering Materials, EarlyView.A self‐consistent autonomous workflow for EBSP‐based microstructure segmentation by integrating PCA, GMM clustering, and cNMF with information‐theoretic parameter selection, requiring no user input. An optimal ROI size related to characteristic grain size is identified.
Qi Zhang +4 more
wiley +1 more source
Hyper-parameter Tuning for Quantum Support Vector Machine
Advances in Electrical and Computer Engineering, 2022 In recent years, the positive effect of quantum techniques on machine learning methods have been studied. Especially in training big data, quantum computing is beneficial in terms of speed.
DEMIRTAS, F., TANYILDIZI, E.
doaj +1 more source
Inefficiency of K-FAC for Large Batch Size Training
, 2019 In stochastic optimization, using large batch sizes during training can leverage parallel resources to produce faster wall-clock training times per training epoch.
Gholami, Amir +6 more
core +1 more source