First of all, I would like to thank Element14 for sponsoring this RoadTest. It's always exciting to try out new products and think of new and interesting ways to put them to use.
I plan to road test the Raspberry Pi 3 by creating a "pattern recognition sensor" using Hierarchical Temporal Memory (HTM). Numenta's Nupic is an open source software which uses HTM to analyze data and recognize patterns. Basically, it creates a model of the neocortex of the human brain and uses that model to "learn" patterns. I would like to port this to the Raspberry Pi and use it to recognize speech patterns. For example, I would like to program it to recognize my voice and perform a task when I say a certain key word. I think that this would be an excellent test of the Raspberry Pi 3's capabilities.
The key tasks in this project are:
1. Port the Nupic software to run on the Raspberry Pi 3. A brief search of the Numenta website shows this has at least been attempted before
2. Convert the microphone input of the Pi into a format suitable for Nupic
3. Use the machine learning capabilities of Nupic to teach it my voice and a few key words
4. Write a python script to take the output of the Nupic software and decide when to execute the required task upon sensing one of the key words has been received
I suspect that the biggest challenge of all will be learning how to use the Nupic software. While I've known about it for several years (I read about it in an issue of IEEE Spectrum), I haven't sat down and really used the software. However, the videos of the software in action are quite impressive. I hope this road test will be fun and exciting for my fellow Element14 members and they will become as excited about this technology as I am.