Learning Generative State Space Models for Active Inference
نویسندگان
چکیده
منابع مشابه
Approximate inference for state-space models
This thesis is concerned with state estimation in partially observed diffusion processes with discrete time observations. This problem can be solved exactly in a Bayesian framework, up to a set of generally intractable stochastic partial differential equations. Numerous approximate inference methods exist to tackle the problem in a practical way. This thesis introduces a novel deterministic app...
متن کاملLearning and Inference in Nonlinear State-Space Models
We present nonlinear state-space models (NSSMs) as a general method for the probabilistic modelling of sequences and time-series. NSSMs take the form of iterated maps on continuous state-spaces, and can have either discrete or continuous valued output functions. They are generalizations of the more well known state-space models such as Hidden Markov models (HMMs), and Kalman Filter Models (KFMs...
متن کاملBayesian Deep Generative Models for Semi-Supervised and Active Learning
Despite the recent successes in machine learning, there remain many open challenges. Arguably one of the most important and interesting open research problems is that of data efficiency. Supervised machine learning models, and especially deep neural networks, are notoriously data hungry, often requiring millions of labeled examples to achieve desired performance. However, labeled data is often ...
متن کاملVariational Learning for Switching State-Space Models
We introduce a new statistical model for time series that iteratively segments data into regimes with approximately linear dynamics and learnsthe parameters of each of these linear regimes. This model combines and generalizes two of the most widely used stochastic time-series models -- hidden Markov models and linear dynamical systems -- and is closely related to models that are widely used in ...
متن کاملGenerative Adversarial Active Learning
We propose a new active learning by query synthesis approach using Generative Adversarial Networks (GAN). Different from regular active learning, the resulting algorithm adaptively synthesizes training instances for querying to increase learning speed. We generate queries according to the uncertainty principle, but our idea can work with other active learning principles. We report results from ...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: Frontiers in Computational Neuroscience
سال: 2020
ISSN: 1662-5188
DOI: 10.3389/fncom.2020.574372