Results 101 to 110 of about 109,092 (251)

Hyperparameters: Optimize, or Integrate Out? [PDF]

, 1996
I examine two approximate methods for computational implementation of Bayesian hierarchical models, that is, models which include unknown hyperparameters such as regularization constants. In the ‘evidence framework’ the model parameters are integrated over, and the resulting evidence is maximized over the hyperparameters.
openaire   +1 more source

Continual Learning for Multimodal Data Fusion of a Soft Gripper

Advanced Robotics Research, EarlyView.
Models trained on a single data modality often struggle to generalize when exposed to a different modality. This work introduces a continual learning algorithm capable of incrementally learning different data modalities by leveraging both class‐incremental and domain‐incremental learning scenarios in an artificial environment where labeled data is ...
Nilay Kushawaha, Egidio Falotico
wiley   +1 more source

Hyperparameter Optimization Across Problem Tasks

, 2018
Hyperparameter Optimization is a task that is generally hard to accomplish as the correct setting of hyperparameters cannot be learned from the data directly. However, finding the right hyperparameters is necessary as the performance on test data can differ a lot under various hyperparameter settings.
Schilling, Nicolas, Windler, Torben, Schmidt-Thieme, Lars   +2 more
openaire   +2 more sources

ChicGrasp: Imitation‐Learning‐Based Customized Dual‐Jaw Gripper Control for Manipulation of Delicate, Irregular Bio‐Products

Advanced Robotics Research, EarlyView.
Automated poultry processing lines still rely on humans to lift slippery, easily bruised carcasses onto a shackle conveyor. Deformability, anatomical variance, and hygiene rules make conventional suction and scripted motions unreliable. We present ChicGrasp, an end‐to‐end hardware‐software co‐designed imitation learning framework, to offer a ...
Amirreza Davar, Zhengtong Xu, Siavash Mahmoudi, Pouya Sohrabipour, Chaitanya Pallerla, Yu She, Wan Shou, Philip Glen Crandall, Dongyi Wang   +8 more
wiley   +1 more source

A Balanced Approach of Rapid Genetic Exploration and Surrogate Exploitation for Hyperparameter Optimization

IEEE Access
This paper introduces a novel approach to hyperparameter optimization (HPO), proposing a methodology that balances exploration and exploitation to enhance optimization performance.
Chul Kim, Inwhee Joe
doaj   +1 more source

Deep Learning Approach for Predicting Efficiency in Organic Photovoltaics from 2D Molecular Images of D/A Pairs

Advanced Theory and Simulations, EarlyView.
This study highlights the potential of deep learning, particularly Convolutional Neural Networks (CNNs), for predicting the photovoltaic performance of organic solar cells. By leveraging 2D images representing donor/acceptor molecular pairs, the model accurately estimates key performance indicators proving that this image‐based approach offers a fast ...
Khoukha Khoussa, Patrick Lévêque, Larbi Boubchir   +2 more
wiley   +1 more source

Ensemble effort estimation with metaheuristic hyperparameters and weight optimization for achieving accuracy.

PLoS ONE
Software development effort estimation (SDEE) is recognized as vital activity for effective project management since under or over estimating can lead to unsuccessful utilization of project resources.
Anum Yasmin, Wasi Haider Butt, Ali Daud
doaj   +1 more source

Squirrel: A Switching Hyperparameter Optimizer

, 2020
In this short note, we describe our submission to the NeurIPS 2020 BBO challenge. Motivated by the fact that different optimizers work well on different problems, our approach switches between different optimizers. Since the team names on the competition's leaderboard were randomly generated "alliteration nicknames", consisting of an adjective and an ...
Awad, Noor, Shala, Gresa, Deng, Difan, Mallik, Neeratyoy, Feurer, Matthias, Eggensperger, Katharina, Biedenkapp, Andre', Vermetten, Diederick, Wang, Hao, Doerr, Carola, Lindauer, Marius, Hutter, Frank   +11 more
openaire   +2 more sources

Multi‐Site Transfer Classification of Major Depressive Disorder: An fMRI Study in 3335 Subjects

Advanced Science, EarlyView.
The study proposes graph convolution network with sparse pooling to learn the hierarchical features of brain graph for MDD classification. Experiment is done on multi‐site fMRI samples (3335 subjects, the largest functional dataset of MDD to date) and transfer learning is applied, achieving an average accuracy of 70.14%.
Jianpo Su, Jian Qin, Hui Shen, Ling‐Li Zeng, Baojuan Li, Jin Liu, Xuemei Song, Li Liu, Weidan Pu, Tongjian Bai, Huaning Wang, Hong Yin, Kai Wang, Lingjiang Li, Dewen Hu   +14 more
wiley   +1 more source

Application of a novel deep learning method for electricity theft detection based on explainable artificial intelligence [PDF]

AIP Advances
To address the challenges of weak feature representation, difficult extraction, and insufficient classification accuracy in electricity consumption time-series data for smart grid security monitoring, this paper proposes a temporal convolutional network (
Yang Liupeng, Feng Chi, Shen Tong, Wang Kun, Dong Hao, Qiao Yuqing, Xing Pengwei, Sun Zhao   +7 more
doaj   +1 more source