Transforming hierarchical images to program expressions using deep networks

0500123 - ÚI 2019 CZ eng V - Research Report
Křen, Tomáš
Transforming hierarchical images to program expressions using deep networks.
Prague: ICS CAS, 2018. 12 s. Technical report, V-1263.
R&D Projects: GA ČR(CZ) GA18-23827S
Institutional support: RVO:67985807
Keywords : deep networks * automatic program synthesis * image processing
OECD category: Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

We present a technique describing how to effectively train a neural network given an image to produce a formal description of the given image. The basic motivation of the proposed technique is an intention to design a new tool for automatic program synthesis capable of transforming sensory data (in our case static image, but generally a phenotype) to a formal code expression (i.e. syntactic tree of a program), such that the code (from evolutionary perspective a genotype) evaluates to a value that is similar to the input data, ideally identical. Our approach is partially based on our technique for generating program expressions in the context of typed functional genetic programming. We present promising results evaluating a simple image description language achieved with a deep network combining convolution encoder of images and recurrent decoder for generating program expressions in the sequential prefix notation and propose possible future applications.
Permanent Link: http://hdl.handle.net/11104/0292265