ScholarGate
Ассистент

Сравнение методов

Просматривайте выбранные методы рядом; строки с различиями подсвечены.

Капсульная сеть×Нейросетевой поиск архитектур×
ОбластьГлубокое обучениеГлубокое обучение
СемействоMachine learningMachine learning
Год появления20172017
Автор методаSabour, S., Frosst, N. & Hinton, G. E.Zoph, B. & Le, Q.V.
ТипDeep learning architecture (vector capsules with dynamic routing)Automated architecture optimization (deep learning)
Основополагающий источникSabour, S., Frosst, N. & Hinton, G. E. (2017). Dynamic Routing Between Capsules. Advances in Neural Information Processing Systems (NeurIPS). link ↗Zoph, B. & Le, Q.V. (2017). Neural Architecture Search with Reinforcement Learning. ICLR. link ↗
Другие названияKapsül Ağı (CapsNet), CapsNet, capsule net, dynamic routing networkNöral Mimari Arama (NAS), NAS, automated architecture design, differentiable architecture search
Связанные45
СводкаA Capsule Network (CapsNet) is a deep learning architecture introduced by Sara Sabour, Nicholas Frosst and Geoffrey Hinton in 2017 that organises neurons as vectors (capsules) rather than scalar activations, so that spatial hierarchy and pose (orientation) information are encoded directly. It was proposed to overcome the fragility of convolutional networks to changes in viewpoint.Neural Architecture Search (NAS), introduced by Zoph and Le in 2017, automatically optimizes architectural decisions such as a network's depth, width, and connection structure instead of hand-designing them. Leading methods in the field include DARTS, ENAS, and Once-for-All.
ScholarGateНабор данных
  1. v1
  2. 2 Источники
  3. PUBLISHED
  1. v1
  2. 2 Источники
  3. PUBLISHED

Перейти к поиску Скачать слайды

ScholarGateСравнение методов: Capsule Network · Neural Architecture Search. Получено 2026-06-18 из https://scholargate.app/ru/compare