News for hackers. Stuff that matters.
Re:Neurosymbolic AI – Combining neural nets and symbolic AI by mark_l_watson on Monday October 19, 2020 @09:08AM (#24825971)
This article started slow for me, I almost stopped reading, glad I didn’t. Great read when the discussion got into the CLEVR data sets and hybrid system.

Hybrid AI has been a keen interest after I retired from almost 5 years of work with deep learning. I just took a job on a knowledge graph team and it feels great to be working on a different approach to knowledge representation and reasoning. My personal opinion is that Hybrid AI is the future and I wouldn’t be surprised to see an exponential growth of practical results, similar to what happened with deep learning around 2013.

Re:Neurosymbolic AI – Combining neural nets and symbolic AI by yazr on Monday October 19, 2020 @09:47AM (#24826309)
Many had the same thought after AlphaZero i.e. some sort of expert-iteration for any (formal/combinatorial) domain what can be tree-searched

But it turns out, that interesting problems have existing refined algorithms that are difficult to beat

I agree that (DL + something) is the next step

Do you lean more towards symbolic search + neural heuristic or neural representation of symbolic domain ?

Re:Neurosymbolic AI – Combining neural nets and symbolic AI by mark_l_watson on Monday October 19, 2020 @01:22PM (#24828567)
I lean towards symbolic AI + neural models. There is an architecture diagram in the article showing one good example.