Internal Reinforcement in a Connectionist Genetic Programming Approach Astro Teller ABSTRACT: Genetic programming (GP) is a successful machine learning technique that provides powerful parameterized primitive constructs using evolution as its search mechanism. However, unlike some machine 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 past performance. GP is missing a clear, locally optimal update procedure, the equivalent of gradient-descent backpropagation for ANNs. In this talk, I will discuss ``Neural Programming,'' a connectionist representation for evolving parameterized programs. Neural Programming allows for the generation of credit and blame assignment in the process of learning programs. I will also detail ``Internal Reinforcement,'' a general informed feedback mechanism for Neural Programming. After I present the Internal Reinforcement process, I'll show a few experimental results demonstrating its increased learning rate.