4 votes

Has machine learning been combined with logical reasoning (for example, PROLOG)?

In reference to your exact question, there is published research that attempts to bring these two areas together. For example, HolStep: A Machine Learning Dataset for Higher-order Logic Theorem ...
jsimmons's user avatar
3 votes

Can (trained) neural networks be combined with symbolic AI to perform operations like AND?

I think you would be interested in Neural-Symbolic Learning and Reasoning, a recent survey on the intersection between connectionist models (e.g. neural nets) and symbolic reasoning. It's a long paper,...
Philip Raeisghasem's user avatar
2 votes

Has machine learning been combined with logical reasoning (for example, PROLOG)?

Another example where machine learning has been combined with symbolic AI is in the context of knowledge graphs (which can be viewed as a graphical/visual representation of a knowledge base), where ...
nbro's user avatar
  • 40.6k
1 vote

What is the "state of the art" in (at least partially) symbolic/logic-based chat bots/AI assistants?

In recent times, 'neural-symbolic' approaches have again increasingly emerged that are used in the different parts of dialogue systems, e.g. NLU (Intent/Slot), Semantic Parsing, Dialog State Tracking, ...
SvshX's user avatar
  • 11
1 vote

What is the difference between Neurosymbolic AI and Transformer AI

There is a big difference between Neurosymbolic AI and transformer AI. Neurosymbolic AI is more rule-based and logical, while transformer AI is more creative and can learn from data. Neurosymbolic AI ...
Faizy's user avatar
  • 1,114
1 vote

In what ways can connectionist AI be integrated with GOFAI?

A neural net with even a single hidden layer is capable of Universal function approximation - it can approximate any continuous function 'as closely as you like'. Hence, one option would be to look ...
NietzscheanAI's user avatar

Only top scored, non community-wiki answers of a minimum length are eligible