Neurosymbolic Programming (NP) techniques have the potential to accelerate scientific discovery. These models combine neural and symbolic components to learn complex patterns and representations from data, using high-level concepts or known constraints. NP techniques can interface with symbolic domain knowledge from scientists, such as prior knowledge and experimental context, to produce interpretable outputs. We identify opportunities and challenges between current NP models and scientific workflows, with real-world examples from behavior analysis in science: to enable the use of NP broadly for workflows across the natural and social sciences.
It's a combination of GOFAI (fancy tree search) and ML (neural networks and differentiable programming)
The idea isn't particularly new but it wasn't possible to implement anything useful until recently when attention/transformers and LLMs gave a huge boost to NLP and most ML tasks.
The algorithms are generally in the area of machine learning + programming languages and pretty flexible. This paper talks about how we "bias" these algorithms for applications in the hard sciences (specifically talking about behavioral neuroscience but has/is being applied in other areas as well).
