Astro Teller

ICML Conference 2000 Conference Paper

Efficient Learning Through Evolution: Neural Programming and Internal Reinforcement

• Astro Teller
• Manuela Veloso

AIJ Journal 2000 Journal Article

Internal reinforcement in a connectionist genetic programming approach

• Astro Teller
• Manuela Veloso

Genetic programming (GP) can learn complex concepts by searching for the target concept through evolution of a population of candidate hypothesis programs. However, unlike some learning techniques, such as Artificial Neural Networks (ANNs), GP does not have a principled procedure for changing parts of a learned structure based on that structure's performance on the training data. GP is missing a clear, locally optimal update procedure, the equivalent of gradient-descent backpropagation for ANNs. This article introduces a new algorithm, “internal reinforcement”, for defining and using performance feedback on program evolution. This internal reinforcement principled mechanism is developed within a new connectionist representation for evolving parameterized programs, namely “neural programming”. We present the algorithms for the generation of credit and blame assignment in the process of learning programs using neural programming and internal reinforcement. The article includes a comprehensive overview of genetic programming and empirical experiments that demonstrate the increased learning rate obtained by using our principled program evolution approach.

IJCAI Conference 1997 Conference Paper

Algorithm Evolution for Signal Understanding

• Astro Teller

AAAI Conference 1996 Short Paper

Algorithm Evolution for Signal Understanding

• Astro Teller

Automated program evolution has existed in some form for over thirty years. Signal understanding (e.g., signal classification) has been a scientific concern for even longer than that. Interest in generating, through machine learning techniques, a general signal understanding system is a newer topic, but has recently attracted considerable attention. First, I have proposed to define and create a machine learning mechanism for generating signal understanding systems independent of the signal' s type and size. Second, I have proposed to do this through an evolutionary strategy that is an extension of genetic programming. Third, I have proposed to introduce a suite of sub-mechanisms that not only contribute to the power of the thesis mechanism, but are also contributions to the understanding of the learning technique developed.