Population-based Incremental Learning is shown require very sensitive scaling of its learning rate. The learning rate must scale with the system size in a problem-dependent way. This is shown in two problems: the needle-in-a haystack, in which the learning rate must vanish exponentially in the system size, and in a smooth function in which the learning rate must vanish like the square root of t...

Twenty-five older and 25 younger adults were compared on declarative (i.e., Rey Auditory-Verbal Learning Test and Visual Pair Associations) and procedural (i.e., Tower of Hanoi puzzle and Porteus mazes) learning tasks. A dissociation between learning rate on declarative and procedural tasks was demonstrated for the elderly participants. The younger group showed a steeper learning rate than the ...

In this paper we propose a framework for developing globally convergent batch training algorithms with adaptive learning rate. The proposed framework provides conditions under which global convergence is guaranteed for adaptive learning rate training algorithms. To this end, the learning rate is appropriately tuned along the given descent direction. Providing conditions regarding the search dir...

This paper reports an attempt to apply a simple association learning model to the analysis of the influence of response and training variables on paired-associate learning. The issues under investigation are old ones but have not been resolved satisfactorily in the past. With the aid of the elementary learning model, the problems are posed clearly and, the data willing, adequately resolved by t...

Abstract. Adaptive inverse control of linear system with fixed learning rate least mean square (LMS) algorithm is improved by varying the learning rate. This variable learning rate LMS algorithm is proved to be convergent by using Lyapunov method. It has better performance especially when there is noise in command input signal. And it is simpler than the Variable Step-size Normalized LMS algori...