Using inductive types for ensuring correctness of neuro-symbolic computations
Ekaterina Komendantskaya, K. Broda, Artur d’Avila Garcez · City Research Online (City University London) · 2010
Abstract. We propose a new method for ensuring correctness of neuro-symbolic computations. We consider important examples when checking the data type of the network’s inputs/outputs is crucial for ensuring that it performs correctly. We construct neuro-symbolic networks that can recognise the type of the input/output data; they are capable of recognising inductive and even dependent types.