Schemas and Genetic Programming (1995)
Abstract:
With the help of schemas and genetic programming we describe systems which ffl interact with the real world ffl make theories about the consequences of their actions and ffl dynamically adjust inductive bias. We present experimental data related to learning geometric concepts and moving a block in a microworld. 1 Introduction To investigate the mechanisms which enable systems to learn is among the most challenging of research activities. In computer science alone it is pursued by at least three communities [Car90], [Nat91], [Rit91]. The overwhelming majority of all studies treats situations with strong inductive bias, i.e. there is a fairly narrow class H of algorithms and the concept or algorithm to be learned is known a priori to lie in that class H . With the help of schemas in the sense of Drescher [Dre91] and genetic programming [Koz92] we will describe here systems which 1. interact with the real world via effectors and sensors, 2. make theories about the consequences ...
Citations
| 713 | Genetic Programming – Koza - 1992 |
| 142 | Made-up minds, a constructivist approach to artificial intelligence – Drescher - 1991 |
| 10 | Learning Geometric Concepts with an Evolutionary Algorithm – Birk - 1996 |
| 9 | Autonomous theory building systems – Paul, Solomonoff - 1991 |
| 3 | Gesammelte Werke – Piaget - 1991 |
| 1 | Stimulus Response Learning of Eye-Hand-coordination; AI-lab memo 12-96, under review; Vrije Universiteit – Birk, Paul - 1997 |
| 1 | Natarajan; Machine Learning, A theoretical approach – Balas - 1991 |
| 1 | Schulten, Thomas Martinetz; Neuronale Netze – Ritter, Klaus - 1991 |

