You can add location information to your Tweets, such as your city or precise location, from the web and via third-party applications. You always have the option to delete your Tweet location history. Learn more
Deep learning excels at unlocking the creation of impressive early demos of new applications using very little development resources. The part where it struggles is reaching the level of consistent usefulness and reliability required by production usage.
Autonomous driving is the ultimate example. You could use deep learning to create an impressive self-driving car prototype in 2015 on a shoestring budget (Comma did exactly that, using Keras). Five years and billions of $ later, the best DL-centric driving systems are still L2+.
Every app demo based on GPT-3 follows this pattern. You can build the demo in a weekend, but if you invest $20M and 3 years fleshing out the app, it's unlikely it will still be using GPT-3 at all, and it may ever meet customer requirements
The reason why is that parametric models trained with gradient descent make it easy to automate something, but have little ability to deviate from the patterns they've learned. Meanwhile, the real world is full of surprises, and handling it requires the ability to adapt.
Which are all reasons to use Information Theory. This is a clear well-define, mathematical framework, featuring formulae that are used independently showing their usefulness. Kullback Leibler Divergence and Mutual information are even used in climate science!! >>
it gets exponentially hard to achieve perfection
Even to get to predictability it appears.
That’s where we struggle all the time...
Freeman Dyson wrote a review on Information Theory in the New York Review of Books, dealing with communication:https://boingboing.net/2011/02/27/freeman-dyson-review.html …
That's absolutely been the experience! Consistent usefulness and reliability out of DL is a big challenge.
Fully agree. Run into situations at work where I read an impressive dl paper and try to put a prototype of it into production only to realize that what looked good about the findings only did so on paper i.e. very difficult to get working in production
Twitter may be over capacity or experiencing a momentary hiccup. Try again or visit Twitter Status for more information.
