Dynamic Memory Networks for Visual and Textual Question Answering · HackerPapers discussions

Dynamic Memory Networks for Visual and Textual Question Answering — mentioned by sapphireblue

Mon, 26 Sep 2016 21:18:24 GMT

I disagree. There exist examples of system displaying very non-trivial, open-ended behavior, and yet they are still not agi. A good example of this is https://arxiv.org/abs/1603.01417 . When trained it is able to answer free-form questions about images.

Paper and discussion history. A mention is not an endorsement.

Dynamic Memory Networks for Visual and Textual Question Answering — mentioned by sapphireblue

Sun, 31 Jul 2016 20:33:18 GMT

3 years ago many systems that exist today would be regarded as "scifi" or "maybe 10 years into the future". One of the most striking examples is Visual Question Answering with dynamic memory networks [1]. The model is given raw pixels and encoded question in natural language, it should output a natural language answer. See how it works on data it hasn't seen: http://i.imgur.com/074G9pg.jpg Do not underestimate what good ML model can learn given enough data. And in case of online shopping there usually is more than enough data, and big companies like Amazon have been using ML (context bandits)…

Paper and discussion history. A mention is not an endorsement.

Dynamic Memory Networks for Visual and Textual Question Answering — HN submission

Mon, 07 Mar 2016 04:35:50 GMT

Dynamic Memory Networks for Visual and Textual Question Answering

122 points; 15 discussion replies on HN. Paper and source history. A submission is not an endorsement.