saip
Joined 10 years ago
Karma
441
Submissions
52
Member since
May 15
Recent submissions
Comment · 8 years ago
Access to parallel corpora is a limiting factor in general. A good way to train a language translator is to use an open source dataset (several here http://opus.nlpl.eu/) to train a base model, and then fine-tune it with a smaller dataset specific to your domain.
In this case, the author claims pretty good accuracy, almost on par with Google Brain's!
On my test set of 3,000 sentences, the translator obtained a BLEU score of 0.39. This score is the benchmark scoring system used in machine translation, and the current best I could find in English to French is around 0.42 (set by some smart folks as Google Brain). So, not bad.Comment · 9 years ago
A GAN style approach to learning and generating variants could be interesting as well. It could generate a couple of hundred plausible versions. Then you have another network that is trained to differentiate between fake and real colored photos which picks the best version.
Comment · 9 years ago
Agreed. I imagine this has applications in compression as well. You could stream a movie (or a football game) in black and white and enable each device to color it on the spot. A similar technique could also be done for HD/3D/VR.
Comment · 9 years ago
Hey, thanks! I'm one of the co-founders at FloydHub.
Our focus has been on individual data scientists thus far. We'll be rolling out a teams plan soon since folks doing deep learning at work (with on-prem or cloud infra) tend to run into more or less the same difficulties as individuals. If you have any feedback, I'd love to hear :) sai (at) floydhub.com
Deep learning research @Bing, Microsoft '10-'16
Stanford AI Lab '10 (advised by Andrew Ng)
CS @IIT Kharagpur
Email: sai (at) floydhub.com
LinkedIn: https://www.linkedin.com/in/saiprashanths