Results 61 to 70 of about 118,488 (274)

Dropout Inference in Bayesian Neural Networks with Alpha-divergences

CoRR, 2017
To obtain uncertainty estimates with real-world Bayesian deep learning models, practical inference approximations are needed. Dropout variational inference (VI) for example has been used for machine vision and medical applications, but VI can severely underestimates model uncertainty.
Li, Y, Gal, Y
openaire   +4 more sources

Smart Closed‐Loop Systems in Personalized Healthcare: Advances and Outlook

Advanced Materials Technologies, EarlyView.
A smart closed‐loop e‐textile integrates multimodal sensing, onboard processing, wireless communication, and wearable power to enable real‐time physiological/biochemical monitoring and feedback‐controlled therapy. ABSTRACT Smart textiles represent a revolutionary frontier in healthcare, seamlessly blending fabric and advanced technologies to create ...
Safoora Khosravi, Sang Won Lee, Mohammad Abrar Uddin, Sina Hassanpoor, Neha Suvindran, Katherine Le, Harun Arkaz, Harishkumar Narayana, Saeid Soltanian, Danial Khorsandi, Negar Hosseinzadeh Kouchehbaghi, Taeil Kim, Yangzhi Zhu   +12 more
wiley   +1 more source

Uncertainty quantification in multi-class image classification using chest X-ray images of COVID-19 and pneumonia

Frontiers in Artificial Intelligence
This paper investigates uncertainty quantification (UQ) techniques in multi-class classification of chest X-ray images (COVID-19, Pneumonia, and Normal).
Albert Whata, Katlego Dibeco, Kudakwashe Madzima, Ibidun Obagbuwa   +3 more
doaj   +1 more source

Additive Ensemble Neural Networks

IEEE Access, 2020
Deep neural networks (DNNs) have been making progress in many ways. DNNs are typically used to model complex nonlinearity of high-dimensional data in regression or classification problems.
Minyoung Park, Seungyeon Lee, Sangheum Hwang, Dohyun Kim   +3 more
doaj   +1 more source

Hybridized sine cosine algorithm with convolutional neural networks dropout regularization application

Scientific Reports, 2022
Deep learning has recently been utilized with great success in a large number of diverse application domains, such as visual and face recognition, natural language processing, speech recognition, and handwriting identification.
Nebojsa Bacanin, Miodrag Zivkovic, Fadi Al-Turjman, K. Venkatachalam, Pavel Trojovský, Ivana Strumberger, Timea Bezdan   +6 more
doaj   +1 more source

Super-resolution and uncertainty estimation from sparse sensors of dynamical physical systems

Frontiers in Water, 2023
The goal of this study is to leverage emerging machine learning (ML) techniques to develop a framework for the global reconstruction of system variables from potentially scarce and noisy observations and to explore the epistemic uncertainty of these ...
Adam M. Collins, Peter Rivera-Casillas, Sourav Dutta, Orie M. Cecil, Andrew C. Trautz, Matthew W. Farthing   +5 more
doaj   +1 more source

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

An Empirical Investigation of Catastrophic Forgetting in Gradient-Based Neural Networks [PDF]

, 2015
Catastrophic forgetting is a problem faced by many machine learning models and algorithms. When trained on one task, then trained on a second task, many machine learning models "forget" how to perform the first task.
Bengio, Yoshua, Courville, Aaron, Goodfellow, Ian J., Mirza, Mehdi, Xiao, Da   +4 more
core  

Data Dropout: Optimizing Training Data for Convolutional Neural Networks

, 2018
Deep learning models learn to fit training data while they are highly expected to generalize well to testing data. Most works aim at finding such models by creatively designing architectures and fine-tuning parameters.
Huan, Jun, Li, Bo, Wang, Tianyang
core   +1 more source

Consensus Formation and Change are Enhanced by Neutrality

Advanced Science, EarlyView.
Neutral agents are shown to enhance both the formation and overturning of consensus in collective decision‐making. A general mathematical model and experiments with locusts and humans reveal that neutrality enables robust consensus via simple interactions and accelerates consensus change by reducing effective population size.
Andrei Sontag, Janina A. Hoffmann, Tim Rogers, Christian A. Yates   +3 more
wiley   +1 more source