Порівняння методів

	Генеративна модель на основі градієнта (Score-Based Generative Model)	Капсульна мережа
Галузь	Глибоке навчання	Глибоке навчання
Родина	Machine learning	Machine learning
Рік появи	2019	2017
Автор методу	Song, Y. & Ermon, S.	Sabour, S., Frosst, N. & Hinton, G. E.
Тип	Score-based generative model (SDE framework)	Deep learning architecture (vector capsules with dynamic routing)
Основоположне джерело	Song, Y. & Ermon, S. (2019). Generative Modeling by Estimating Gradients of the Data Distribution. NeurIPS 32, 11895–11907.	Sabour, S., Frosst, N. & Hinton, G. E. (2017). Dynamic Routing Between Capsules. Advances in Neural Information Processing Systems (NeurIPS).
Інші назви	Skor Tabanlı Üretici Model (Score-Based / SDE), score-based diffusion, SDE-based generative model, score SDE	Kapsül Ağı (CapsNet), CapsNet, capsule net, dynamic routing network
Пов'язані	5	4
Підсумок	A score-based generative model, introduced by Yang Song and Stefano Ermon in 2019 and generalized to the stochastic differential equation (SDE) framework in 2021, learns the gradient of the data density — the score — rather than predicting noise directly, and uses it to generate new samples. It is the mathematical generalization that unifies diffusion models under a continuous-time formulation.	A 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.