genericpseudo
Joined 11 years ago
Karma
495
Submissions
146
Member since
Aug 18
Recent submissions
Comment · 8 years ago
I like "Machine Learning: A Probabilistic Perspective" by Kevin Murphy more, but this really is a matter of taste; both are excellent.
Comment · 8 years ago
Take as much probability and linear algebra as you can conveniently do – as much for the intuition as for the symbol-manipulation mechanics – and don't underrate the importance of domain expertise in any problem you get interested in!
Comment · 8 years ago
The Shipping Forecast is a very significant cultural reference in the UK. It crops up all over the place. Britain is _fundamentally_ an island and a seafaring nation, and that's something Americans miss; you're never more than seventy miles from the sea. It's as iconic as, I don't know, Thanksgiving football in the US; it's a thing everyone knows about without explanation.
This is from an album which sold over 1.2m copies in the UK; one of the biggest records of the 90s: https://www.youtube.com/watch?v=SD8gO8TAr4s
Comment · 8 years ago
Density functional theory, for example, is taught at undergraduate level as part of both chemistry and physics triposes. Probably materials science too, and it certainly used to be an option within earth sciences (as part of the mineral physics path).
Comment · 8 years ago
Collaborative filtering is machine learning, so if you consider AI machine learning, definitely yes.
Comment · 8 years ago
The team behind Detectron have published an enormous amount of really good research, but the Detectron codebase struck me as "good research code" rather than something you'd ideally want in production.
Comment · 8 years ago
Not at the kind of resolution you'd want to be using on, e.g., Twitch. In that setting, you could just use chromakey, though? That's '70s technology, cheap and very reliable.
Comment · 8 years ago
If you're interested in this but have no background, the best place to start is "Fully Convolutional Networks for Semantic Segmentation" – https://people.eecs.berkeley.edu/~jonlong/long_shelhamer_fcn...
This is a very active field of research. Another thread worth pulling on is Mask R-CNN: https://arxiv.org/abs/1703.06870
It's not quite as simple as "this one has highest mAP, let's use it"; the tradeoffs are complex. In particular, as you can see in the image here, one thing DeepLab doesn't do is segment instances – so you get a mask of "people", not a mask per person. Mask R-CNN does a better job on that by design, because it predicts both bounding boxes and a mask per bounding box.
Comment · 8 years ago
> Stitch Fix makes it a major brand point that computers are an important part of the process
(which even if you disregard everything else is a really good line to take if you're after recruiting good machine learning engineers!)
Comment · 8 years ago
This means that codec development makes no sense for anyone who doesn't own either a large distribution platform or a large playback platform. (Much of the research has been done by middleware companies attempting to tax the two; their business goes from royalties to work-for-hire, at best, which is way less attractive for them).
This is fine – in a macroeconomic sense – but of course it sucks if you're one of the companies being disrupted.
Comment · 9 years ago
Effective counterexample: the USPS.
Comment · 9 years ago
One of four (MXNet and CNTK alongside TF and Theano), and the Amazon deep learning API forked Keras to default to MXNet support before it was really ready - which irked the Keras authors quite a bit.
Comment · 9 years ago
Python has been the language of choice for many physicists (when not doing Fortran) since the early 2000s.
Comment · 9 years ago
PyTorch, Theano (rip), TensorFlow itself, Numba/Blaze?
Comment · 9 years ago
It's even more dramatic than that. Google make money on advertising, not direct sales, so what you're saying is "the (usage * advertiser desirability) from the entirety of group 2 is roughly equal to groups 1 and 3 combined".
Given group 1 is many times bigger than group 2, that's a very strong statement, but it's borne out in all the data I've ever seen, both public and private.