To enable this approach, we also propose a novel efficient synthesis procedure, which accepts a set of promising program properties, and returns a satisfying neural architecture.
Mathematical theorems are human knowledge able to be accumulated in the form of symbolic representation, and proving theorems has been considered intelligent behavior.
The renaissance of neural architecture search (NAS) has seen classical methods such as genetic algorithms (GA) and genetic programming (GP) being exploited for convolutional neural network (CNN) architectures.
The discovery of new multicomponent inorganic compounds can provide direct solutions to many scientific and engineering challenges, yet the vast size of the uncharted material space dwarfs current synthesis throughput.
Computational Physics Materials Science
Automatic programming, the task of generating computer programs compliant with a specification without a human developer, is usually tackled either via genetic programming methods based on mutation and recombination of programs, or via neural language models.
Although evolutionary-based NAS works were reported to require a considerable amount of GPU time for architecture search, our approach obtained promising results in little time, encouraging further experiments in evolutionary-based NAS, for search and network representation improvements.
Ranked #11 on Neural Architecture Search on CIFAR-100