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
A key design principle I follow in libraries (e.g. Keras) is "progressive disclosure of complexity". Make it easy to get started, yet make it possible to handle arbitrarily flexible use cases, only requiring incremental learning at each step. Like zooming in a complex landscape.pic.twitter.com/AzaySJeTMP
When you zoom in, the incremental complexity is still part of *the same picture*. Everything you're learning in the beginning will still be relevant once you've become an expert. You will be gradually diving into workflows where you're writing more and more logic from scratch.
So with something like Keras, you won't have to switch to an entire different framework as you go from student to researcher, or from data scientist to deep learning engineer.
I think thoughtful design can dramatically broaden the impact and reach of software. There are no complicated ideas in deep learning, only bad interfaces.
Plotting libraries are a great example of what you are saying.
This works really nicely. I recently moved some models to tf.keras, and it’s so simple to get things working. You can add the complexity later.
For details, zoom in. For context, zoom out.
As an exercise you can read this thread and replace “libraries” with “the canon of any discipline “. It’s like a hero’s journey form for mobilizing a set of tools. Very cool.
I can only imagine what the ability to effortlessly jump back and forth across levels of abstraction must feel like. Donald Knuth describes that feeling very well in an episode with @lexfridman.
Genius! Should be common sense.
Would love to see more paper implementations written in keras. Easier for us novices to see what's going on, and improve upon.
Twitter may be over capacity or experiencing a momentary hiccup. Try again or visit Twitter Status for more information.
