Equations of States in Statistical Learning for a Nonparametrizable and Regular Case
نویسنده
چکیده
Many learning machines that have hierarchical structure or hidden variables are now being used in information science, artificial intelligence, and bioinformatics. However, several learning machines used in such fields are not regular but singular statistical models, hence their generalization performance is still left unknown. To overcome these problems, in the previous papers, we proved new equations in statistical learning, by which we can estimate the Bayes generalization loss from the Bayes training loss and the functional variance, on the condition that the true distribution is a singularity contained in a learning machine. In this paper, we prove that the same equations hold even if a true distribution is not contained in a parametric model. Also we prove that, the proposed equations in a regular case are asymptotically equivalent to the Takeuchi information criterion. Therefore, the proposed equations are always applicable without any condition on the unknown true distribution.
منابع مشابه
Recognizing the Emotional State Changes in Human Utterance by a Learning Statistical Method based on Gaussian Mixture Model
Speech is one of the most opulent and instant methods to express emotional characteristics of human beings, which conveys the cognitive and semantic concepts among humans. In this study, a statistical-based method for emotional recognition of speech signals is proposed, and a learning approach is introduced, which is based on the statistical model to classify internal feelings of the utterance....
متن کاملMINIMIZATION OF DETERMINISTIC FINITE AUTOMATA WITH VAGUE (FINAL) STATES AND INTUITIONISTIC FUZZY (FINAL) STATES
In this paper, relations among the membership values of gener- alized fuzzy languages such as intuitionistic fuzzy language, interval-valued fuzzy language and vague language are studied. It will aid in studying the properties of one language when the properties of another are known. Further, existence of a minimized nite automaton with vague ( final) states for any vague regular language recog...
متن کاملUtilizing Generalized Learning Automata for Finding Optimal Policies in MMDPs
Multi agent Markov decision processes (MMDPs), as the generalization of Markov decision processes to the multi agent case, have long been used for modeling multi agent system and are used as a suitable framework for Multi agent Reinforcement Learning. In this paper, a generalized learning automata based algorithm for finding optimal policies in MMDP is proposed. In the proposed algorithm, MMDP ...
متن کاملCitizenship Classes for Bhutanese-Nepali Elders: From Cognitive Deficits to Cultural-Historical Understandings
This article focuses on home-based citizenship classes for Bhutanese-Nepali elders in Central Ohio in the United States. As part of a larger longitudinal study centered in the ethnographic, language socialization, and discourse analytic traditions, the article focuses on data, particularly regular audiovideo recordings, gathered over a five-month period and tracks one student’s progress towards...
متن کاملAn efficient approach for availability analysis through fuzzy differential equations and particle swarm optimization
This article formulates a new technique for behavior analysis of systems through fuzzy Kolmogorov's differential equations and Particle Swarm Optimization. For handling the uncertainty in data, differential equations have been formulated by Markov modeling of system in fuzzy environment. First solution of these derived fuzzy Kolmogorov's differential equations has been found by Runge-Kutta four...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید
ثبت ناماگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید
ورودعنوان ژورنال:
- CoRR
دوره abs/0906.0211 شماره
صفحات -
تاریخ انتشار 2009