Artificial Intelligence with Erlang: The Domain of Relatives (2007)

Re:Artificial Intelligence with Erlang: The Domain of Relati... by CocoaGeek on Friday April 27, 2018 @11:15AM (#16941386)

Logic programming is part of what people now call GOFAI (Good Old Fashion AI). I think it still has a place in building intelligent systems, but these days most people equate AI to Machine Learning, unfortunately ...

[ Parent | on HN ]

Re:Artificial Intelligence with Erlang: The Domain of Relati... by cjauvin on Friday April 27, 2018 @11:28AM (#16941490)

I'm curious, why do you say it's unfortunate? (Don't get me wrong I am also of that opinion, more or less, so I'm just curious about yours)

[ Parent | on HN ]

Re:Artificial Intelligence with Erlang: The Domain of Relati... by vokolk on Saturday April 28, 2018 @01:30AM (#16946205)

Check out this paper by Turin-award winner Judea Pearl for fundamental limitations of current approaches to ML: https://arxiv.org/abs/1801.04016

[ Parent | on HN ]

Re:Artificial Intelligence with Erlang: The Domain of Relati... by fjsolwmv on Sunday April 29, 2018 @12:12AM (#16950669)

I think that argument ignores that neural nets can learn the models that Pearl believes are important. And it's quite plausible that human reasoning works in similar way.

Pearl's career is all about causal networks, so he's slightly biased when it comes to survey like this.

[ Parent | on HN ]

Re:Artificial Intelligence with Erlang: The Domain of Relati... by vokolk on Sunday April 29, 2018 @01:22AM (#16950811)

So you are saying that Pearl's argument that current ML system cannot reason about interventions and retrospection (as he defines them) are wrong?

[ Parent | on HN ]