Meta-learning without memorization

M Yin, G Tucker, M Zhou, S Levine, C Finn - arxiv preprint arxiv …, 2019 - arxiv.org
The ability to learn new concepts with small amounts of data is a critical aspect of
intelligence that has proven challenging for deep learning methods. Meta-learning has …

Attentive weights generation for few shot learning via information maximization

Y Guo, NM Cheung - … of the IEEE/CVF Conference on …, 2020 - openaccess.thecvf.com
Few shot image classification aims at learning a classifier from limited labeled data.
Generating the classification weights has been applied in many meta-learning methods for …

Neural network based image classifier resilient to destructive perturbation influences–architecture and training method

V Moskalenko, A Moskalenko - Radioelectronic and computer systems, 2022 - nti.khai.edu
Modern methods of image recognition are sensitive to various types of disturbances, which
actualize the development of resilient intelligent algorithms for safety-critical applications …

Моделі та методи інтелектуальної інформаційної технології оцінювання функціонального стану труб водовідведення

МО Зарецький - 2023 - essuir.sumdu.edu.ua
Дисертація присвячена розв'язанню актуальної науково-прикладної задачі
автоматизації процесу оцінювання функціонального стану трубопроводу …

[BOEK][B] Variational Methods with Dependence Structure

M Yin - 2020 - search.proquest.com
It is a common practice among humans to deduce, to explain and to make predictions based
on concepts that are not directly observable. In Bayesian statistics, the underlying …