Steps into Parag Mital’s course ‘Creative Applications of Deep Learning in TensorFlow’ on Kadenze. Very slow. A majority of the time is dedicated to learning the tools used in order to get into deep learning & neural networks, namely Python itself (although that has become rather natural), and specific libraries such as NumPy, for many mathematical operations, and MatPlotLib for plotting and statistical graphs. On top of that, I need to refresh my knowledge of matrices, the obvious building block of so much machine learning today. A good YouTube channel for quick recaps of linear algebra, 3Blue1Brown. As usual with a lot of creative coding, I will have to deal with the fact that most resources are dedicated to image processing (even if Natural Language Processing is also an important field). Often this does feel like a waste of time, especially as the mathematical operations are different, but most of what I learn will be necessary anyway. A major issue is to deal with the sense of slowness I get from these learning sessions, where even the simplest concepts and manipulations often require me to ponder, pause and rest for far longer than I would wish.
Other tasks at hand:
- The (hopefully) last step to build complete wordsquare databases (and other word-based ones) is to use the Trie data structure, which allows for a much faster lookup of prefixes (‘dem’ in ‘demon’, ‘ra’ in ‘rage’ …) or entire words than normal look-up (it is, if my research is correct, even faster than looking up for an element in a set() in Python); if I implement the Trie I found for Python and use it to build squares, I might be able to go beyond the mere 3-lettered version I worked with so far;- In the same gesture, I should adapt my wordsquare database builder from C++ (OpenFrameworks) to Python;
- Adapt and expand both the wordlaces and subwords projects, so that I can build up proper databases that will serve as the meat for my coming machine learning beasts.
- Force myself to get into reading papers, rather than just blog posts or video tutorials, even if superficially or slowly at first.