From Deep Learning to Symbolic Learning

The two biggest flaws of deep learning are its lack of model interpretability (i.e. why did my model make that prediction?) and the large amount of data that deep neural networks require in order to learn. Neural nets are data hungry.

Geoff Hinton himself has expressed scepticism about whether backpropagation, the workhorse of deep neural nets, will be the way forward for AI. Research into so-called ‘one-shot learning’ may address deep learning’s data hunger.

But deep learning has its discontents, and many of them look to other branches of AI when they hope for the future. Symbolic reasoning is one of those branches. Symbolic artificial intelligence, also known as Good, Old-Fashioned AI (GOFAI), was the dominant paradigm in the AI community from the post-War era until the late 1980s.

Recent work by MIT, DeepMind and IBM has shown the power of combining connectionist techniques like deep neural networks with symbolic reasoning.

Deep symbolic learning, or enabling deep neural networks to manipulate, generate and otherwise cohabitate with concepts expressed in strings of characters, could help solve explainability, because, after all, humans communicate with signs and symbols, and that is what we desire from machines.