Genome as a functional program
This work addresses a foundational problem in computational biology and AI by proposing a novel theoretical framework, but it appears incremental as it builds on existing concepts like functional programming and information geometry without presenting concrete results or numbers.
The paper tackles modeling the genome as a functional program and frames Darwinian evolution as a learning problem for functional programming, introducing a learning model for a class of functional programs that relates to information geometry and temperature learning.
We discuss a model of genome as a program with functional architecture and consider the approach to Darwinian evolution as a learning problem for functional programming. In particular we introduce a model of learning for some class of functional programs. This approach is related to information geometry -- the learning model uses some kind of distance in the information space (the reduction graph of the model), we consider statistical sum over paths in the reduction graph and discuss relation of this sum to temperature learning.