gfrison1

Computer programming is a specialized activity that requires long training and experience to match productivity, precision and integration. It hasn’t been a secret for AI practitioners to ultimately create software tools that can facilitate the role of programmers. The branch of AI dedicated to automatically generate programs from examples or some sort of specification is called program synthesis. In this dissertation, I’ll explore different methods to combine symbolic AI and neural networks (like large language models) for automatically create programs. The posed question is: How AI methods can be integrated for helping to synthesize programs for a wide range of applications?