Wrapping Up

[00:00:00]
>> We can spend a lot of time on image parts and computer vision, right, and I think that was fun. With text, I tried to shrink everything into limited time we had, but the main point is that probably the most important part with the text analytics is how you preprocess your text.

[00:00:23]
Right, how you simply locating everything and, for instance, you can use word embedding or hot encoding. And that might actually give you different results. And reinforcement learning allows you to simply build this model which will help your agents simply observe the environment and act accordingly. For instance, in simple examples, just move your car to the left or to the right to get a particular goal, in our case is just balanced this pool.

[00:00:55]
But that's the simple examples of how deep learning can be used. And well, I hope you had a lot of fun. [LAUGH] I know we digged a little bit too deep into math at some points, but still I really hope it helped with better understanding what deep learning is and how it can be used.

[00:01:16]
All right then, thank you very much, it was awesome, all right.
>> [APPLAUSE]