Zobrazeno 1 - 3
of 3
pro vyhledávání: '"Marzen, S. E."'
Autor:
Marzen, S. E., Crutchfield, J. P.
Inferring models, predicting the future, and estimating the entropy rate of discrete-time, discrete-event processes is well-worn ground. However, a much broader class of discrete-event processes operates in continuous-time. Here, we provide new metho
Externí odkaz:
http://arxiv.org/abs/2005.03750
Autor:
Marzen, S. E., Crutchfield, J. P.
Reservoir computers (RCs) and recurrent neural networks (RNNs) can mimic any finite-state automaton in theory, and some workers demonstrated that this can hold in practice. We test the capability of generalized linear models, RCs, and Long Short-Term
Externí odkaz:
http://arxiv.org/abs/1910.07663
Autor:
Marzen, S. E., Crutchfield, J. P.
Loosely speaking, the Shannon entropy rate is used to gauge a stochastic process' intrinsic randomness; the statistical complexity gives the cost of predicting the process. We calculate, for the first time, the entropy rate and statistical complexity
Externí odkaz:
http://arxiv.org/abs/1704.04707