Re:Toward a deeper understanding of the way AI agents see th...
by sgt101 on Tuesday November 20, 2018 @02:35AM
(#18492370)
Interesting - I'll have a look for that paper.
There's some good DL Packages in Julia - Knet is very elegant but I have to admit (as a Julia fan) that there are challenges in getting things to run properly. I had a long battle with the linker to get the MAC demo's working properly - resolved with a single line of code - but still... I've used the MXNet wrapper to build a LSTM in the summer as well, and that was much smoother (the network itself didn't perform well on the task I had for it, but that's another issue).
Re:Toward a deeper understanding of the way AI agents see th...
by sgt101 on Tuesday November 20, 2018 @02:43AM
(#18492391)
Did you mean : https://arxiv.org/pdf/1810.02338.pdf ?
There is a new model VQA model for CLVR published in Neural information processing systems this year that gets better results than MAC, but they used specialized visual features. They didn't really explore the impact of using those, but I wonder if some of their performance is due to using them to overcome the systematic issues you brought up.