Сравнение на методи
Прегледайте избраните методи един до друг; редовете с разлики са откроени.
| Динамично вариационно извеждане× | Бейсиански изводи за времеви редове× | |
|---|---|---|
| Област | Бейсови методи | Бейсови методи |
| Семейство | Bayesian methods | Bayesian methods |
| Година на възникване≠ | 2014–2015 | 1989 |
| Създател≠ | Bayer, Osendorfer, Krishnan and colleagues | Mike West and Jeff Harrison |
| Тип≠ | Bayesian approximate inference | Bayesian probabilistic model |
| Основополагащ източник≠ | Krishnan, R. G., Shalit, U., & Sontag, D. (2015). Deep Kalman Filters. NIPS 2015 Workshop on Advances in Approximate Bayesian Inference. link ↗ | West, M. & Harrison, J. (1997). Bayesian Forecasting and Dynamic Models (2nd ed.). Springer. ISBN: 978-0387947259 |
| Други названия | sequential variational inference, temporal variational inference, variational inference for state-space models, DVI | Bayesian time series analysis, Bayesian state-space modeling, probabilistic time series inference, BSTS |
| Свързани | 6 | 6 |
| Резюме≠ | Dynamic variational inference extends the variational inference framework to sequential and time-series settings by positing a structured approximate posterior that respects the temporal ordering of latent states. It jointly learns a generative model of how hidden states evolve over time and a recognition network that maps observed sequences back to those latent states, optimising a sequential evidence lower bound (ELBO). | Time series Bayesian inference applies Bayes' theorem sequentially to time-ordered observations, maintaining a full probability distribution over hidden states and model parameters at every time step. This framework unifies state-space models, dynamic linear models, and particle filters, producing calibrated uncertainty for both filtering (real-time) and retrospective smoothing tasks. |
| ScholarGateНабор от данни ↗ |
|
|