Applying The Learning So Far
Yesterday, I had an opportunity to briefly consider some of the types of data that the MOOVPAD apps will need to handle from technical and user perspectives. The AI learning so far has been very beneficial in terms of understanding how this data can be used to improve service delivery for MOOVPAD users and ensure better system operation overall
In the first larger screenshot above, we can see that I've started to build some new repos for AI class libraries based on this learning, which will tie into previous work I did on neural nets while undertaking a machine learning course (see the bottom left window). The reason I'm building these libraries now is to ensure the information is still fresh in mind, and to be able to add the necessary comments to the code as I go. As the top right window shows in that screenshot, the code provided with the current AI course is excellent, but applicable mainly to this course content, as expected. MOOVPAD libraries will be written in python, C# and C++ for now.
There's also only minimal comments in the course code, because it relies on the presentation of the lecturer. And so rather than continuing to add my comments to this sample code, it's probably better for me to begin building my own libraries that will integrate with the existing neural net objects and framework as necessary. This approach will slow the AI learning plans in the screenshot above, but should provide better final results, directly applicable to MOOVPAD needs (e.g. user experience, security, EDA pipeline, etc).
More soon 🙂
Stay awesome,
EMH
HOW MOOVPAD IS BEING BUILT
For the overview of how MOOVPAD apps are being developed, the reasoning behind particular decisions during development, policies, and more in relation to all the technical things, please see the link to the left.
This will be an ongoing work in progress, and will always be linked to the bottom of each upcoming Blog post.