This is a great introduction to Deep Learning. I know I learned a few things from Phillip.
Some key concepts
- RapidMiner now can do GPU deep learning. Supports NVIDIA.
- Easy: Using already loaded Neural Net operators.
- Harder: Using H20.ai Deep Learning operator.
- Hardest: Using Keras with RapidMiner.
- Keras requires more complex setup with RapidMiner.
- CNN, RNN, LSTM, etc are now available via RapidMiner GUI.
- Keras supports Tensorflow, CNTK, and Theano.
- Need Python v3.5 (see installation guide here).
- ‘Deep’ discussion on Recurrent and Covolutional.
Here’s a nice graphic from KD Nuggets on some basic activation functions. These activiation functions are what switch a neuron on or off in a neural net model.
Introduction to Keras
This is a really great introductory video on Keras and how simple it makes calling complex deep learning libraries like Tensorflow. The 13 year old author builds a great deep learning model in under 100 lines of code.
I do some questions w.r.t. to the AUC score being 1 (that always raised red flags in my mind) but he he does share the code on Github so everyone can follow along.
This is why I like Keras a lot, it’s like H2O.ai and makes the complex work of coding very simple and accessible.
Installing Keras on RapidMiner
If you watched this great introduction on Deep Learning with Keras and RapidMiner here, you probably want to try it out! I’ll warn you though, it’s a bit tricky to get this up and running on a Windows machine.
The best place to read up on how to do it is in this KB thread at the RapidMiner Community. Installing Keras is heavily dependent on the Python version, additional python modules, and operating system versions too. Of course, if you get stuck, the KB article is a great place to post your questions.
Want to leave a comment?
If you want to give me some feedback on this post, please contact me
via email or give me a Tweet ons Twitter