Ideal learning machines

Ideal Learning Machines

We examine the prospects for finding "best possible" or "ideal" computing machines for various learning tasks. For this purpose, several precise senses of "ideal machine" are considered within the context of formal learning theory. Generally negative results are provided concerning the existence of ideal learning-machines in the senses considered. Machines that learn have both technological and...

Learning Machines

Learning the Ideal Evaluation Function

Designing an adequate fitness function requires substantial knowledge of a problem and of features that indicate progress towards a solution. Coevolution takes the human out of the loop by dynamically constructing the evaluation function based on interactions between evolving individuals. A question is to what extent such automatic evaluation can be adequate. We define the notion of an ideal ev...

Universal Learning Machines

All existing learning methods have particular bias that makes them suitable for specific kind of problems. Universal Learning Machine (ULM) should find the simplest data model for arbitrary data distributions. Several ways to create ULMs are outlined, and an algorithm based on creation of new global and local features combined with meta-learning is introduced. This algorithm is able to find sim...

Hybrid learning machines

The concept of machine intelligence (MI) is complex, and thus many theories and definitions have emerged recently. Last few decades have seen a new era of machine intelligence focusing on the principles, theoretical aspects, and design methodology of algorithms gleaned from nature and biology. Examples are artificial neural networks inspired by mammalian neural systems, evolutionary computation...