Less Than One - A radical new technique lets AI learn with practically no data

I came across with this very interesting new idea about training AI with a substantial small data set.

Since we humans sometimes don't even need to see one example of something to recognize it, why should AI be fed with tons of data to identify something?

Here's the 'Less Than One'-Shot Learning: Learning N Classes From M<N Samples original paper.

The A radical new technique lets AI learn with practically no data article explains it all.

./M6

Facial Recognition with Python

While researching for image recognition I came across some very interesting articles about how to perform facial recognition in Python:

./M6

How to perform basic image recognition with the use of Python


While searching for information about image recognition with Python, I've came across with this tutorial, with video explanation.


./M6

Machine Learning with Python

While researching for image recognition in Python, I came across with TensorFlow, they have a tutorial and documented API.
If you'r looking for a fast and simple kick start, check the TensorFlow Image Recognition Python API Tutorial.
If you'r looking for a bit more detail kick start, check Image Recognition with 10 lines of code.
If you'r specifically looking for image recognition, check this.

You can find the TenserFlow framework here and their models here.

./M6