Add to ORKGNeural networks are statistical models and learning rules are estimators. In this paper a theory for measuring generalisation is developed by combining Bayesian decision theory with information geometry. The performance of an estimator is measured by the information divergence between the true distribution and the estimate, averaged over the Bayesian posterior. This unies the majority of error measures currently in use. The optimal estimators also reveal some intricate inter-relationships among information geometry, Banach spaces and sucient statistics.
There is a need to better understand how generalization works in a deep learning model. The goal of ...
This thesis presents a new theory of generalization in neural network types of learning machines. Th...
Information geometry is a method of analyzing the geometrical structure of a family of information s...
Neural networks are statistical models and learning rules are estimators. In this paper a theory for...
The problem of evaluating different learning rules and other statistical estimators is analysed. A n...
Neural networks can be regarded as statistical models, and can be analysed in a Bayesian framework. ...
Neural networks can be regarded as statistical models, and can be analysed in a Bayesian framework. ...
The problem of evaluating dierent learning rules and other statistical estimators is analysed. A new...
A family of measurements of generalisation is proposed for estimators of continuous distributions. I...
A family of measurements of generalisation is proposed for estimators of continuous distributions. I...
Neural network learning rules can be viewed as statistical estimators. They should be studied in Bay...
In statistics it is necessary to study the relation among many probability distributions. Informatio...
A general mathematical framework is developed for learning algorithms. A learning task belongs to ei...
This chapter discusses the role of information theory for analysis of neural networks using differen...
This paper presents a new algorithm based on the theory of mutual information and information geomet...
There is a need to better understand how generalization works in a deep learning model. The goal of ...
This thesis presents a new theory of generalization in neural network types of learning machines. Th...
Information geometry is a method of analyzing the geometrical structure of a family of information s...
Neural networks are statistical models and learning rules are estimators. In this paper a theory for...
The problem of evaluating different learning rules and other statistical estimators is analysed. A n...
Neural networks can be regarded as statistical models, and can be analysed in a Bayesian framework. ...
Neural networks can be regarded as statistical models, and can be analysed in a Bayesian framework. ...
The problem of evaluating dierent learning rules and other statistical estimators is analysed. A new...
A family of measurements of generalisation is proposed for estimators of continuous distributions. I...
A family of measurements of generalisation is proposed for estimators of continuous distributions. I...
Neural network learning rules can be viewed as statistical estimators. They should be studied in Bay...
In statistics it is necessary to study the relation among many probability distributions. Informatio...
A general mathematical framework is developed for learning algorithms. A learning task belongs to ei...
This chapter discusses the role of information theory for analysis of neural networks using differen...
This paper presents a new algorithm based on the theory of mutual information and information geomet...
There is a need to better understand how generalization works in a deep learning model. The goal of ...
This thesis presents a new theory of generalization in neural network types of learning machines. Th...
Information geometry is a method of analyzing the geometrical structure of a family of information s...