Learning and Discovery in Dynamical Systems with Hidden State
نویسندگان
چکیده
We consider the problem of learning in dynamical systems with hidden state. This problem is deemed challenging due to the fact that the state is not completely visible to an outside observer. We explore a candidate algorithm, which we call the Merge-Split algorithm, for learning deterministic automata with observations. This is based on the work of Gavalda et al(2006) which approximates a given Hidden Markov Model (HMM) with a learned Probabilistic Deterministic Finite Automaton (PDFA).
منابع مشابه
Scale-Free Networks Hidden in Chaotic Dynamical Systems
Abstract In this paper, we show our discovery that state-transition networks in several chaotic dynamical systems are “scale-free networks,” with a technique to understand a dynamical system as a whole, which we call the analysis for “Discretized-State Transition” (DST) networks; This scale-free nature is found universally in the logistic map, the sine map, the cubic map, the general symmetric ...
متن کاملStable Rough Extreme Learning Machines for the Identification of Uncertain Continuous-Time Nonlinear Systems
Rough extreme learning machines (RELMs) are rough-neural networks with one hidden layer where the parameters between the inputs and hidden neurons are arbitrarily chosen and never updated. In this paper, we propose RELMs with a stable online learning algorithm for the identification of continuous-time nonlinear systems in the presence of noises and uncertainties, and we prove the global ...
متن کاملThe Exact Solution of Min-Time Optimal Control Problem in Constrained LTI Systems: A State Transition Matrix Approach
In this paper, the min-time optimal control problem is mainly investigated in the linear time invariant (LTI) continuous-time control system with a constrained input. A high order dynamical LTI system is firstly considered for this purpose. Then the Pontryagin principle and some necessary optimality conditions have been simultaneously used to solve the optimal control problem. These optimality ...
متن کاملLearning Latent Variable and Predictive Models of Dynamical Systems
A variety of learning problems in robotics, computer vision and other areas of artificial intelligence can be construed as problems of learning statistical models for dynamical systems from sequential observations. Good dynamical system models allow us to represent and predict observations in these systems, which in turn enables applications such as classification, planning, control, simulation...
متن کاملA New View of Predictive State Methods for Dynamical System Learning
Recently there has been substantial interest in predictive state methods for learning dynamical systems: these algorithms are popular since they often offer a good tradeoff between computational speed and statistical efficiency. Despite their desirable properties, though, predictive state methods can sometimes be difficult to use in practice. E.g., in contrast to the rich literature on supervis...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
عنوان ژورنال:
دوره شماره
صفحات -
تاریخ انتشار 2007