This paper deals with the evolutionary design of programs (constructors) that are able to create (n+2)-input circuits from n-input circuits. The growing circuits are composed of p...
This paper presents a new method — the Time-delay Added Evolutionary Forecasting (TAEF) method — for time series prediction which performs an evolutionary search of the minimu...
Tiago A. E. Ferreira, Germano C. Vasconcelos, Paul...
Code bloat, the excessive increase of code size, is an important issue in Genetic Programming (GP). This paper proposes a theoretical analysis of code bloat in the framework of sy...
Sylvain Gelly, Olivier Teytaud, Nicolas Bredeche, ...
Recurrent neural networks are theoretically capable of learning complex temporal sequences, but training them through gradient-descent is too slow and unstable for practical use i...
This paper presents a novel approach of applying both positive selection and negative selection to supervised learning for anomaly detection. It first learns the patterns of the n...