A collection of 8 posts
It would be a bit of an understatement to say that machine learning is hot right now. Both my bachelors degree and my PhD were (broadly) in Artificial Intelligence, so once upon a time it was a subject I was reasonably up to date on. I decided it was time to get back up to date.
Right now Python feels like the language of deep learning and data science in general. That’s not really surprising. With the right libraries (probably NumPy, Pandas and MatPlotLib) it can come close to matching Matlab for power and expressibility…
Well. This is embarrassing. At the beginning of last year I was working my way through fast.ai’s excellent Deep Learning for Coders course. Then, around the time I was due to start the last module, my life got…
My mostly unsuccessful attempt to use the part of speech tagging to reduce ambiguity and improve performance in IMDB review classification with RNNs.
Hacks, improvements and graphs. Lots of graphs. Part 2 of my attempt to grapple with the Kaggle Yelp Restaurant Photo Classification competition, using the techniques (and code library) from fast.ai’s “Practical Deep Learning for Coders” course.
Part 1 of my attempt to grapple with the Kaggle Yelp Restaurant Photo Classification competition, using the techniques (and code library) from fast.ai’s “Practical Deep Learning for Coders” course.
Getting started with the fast.ai "Deep Learning for Coders" MOOC. Setting Paperspace to work as a compute backend, and using the iPad app Juno as the frontend.
Notes on the Coursera Speciality which acts as a follow up to the Machine Learning course I discussed previously.
Some notes on the MOOC which is more or less the standard text for basic machine learning. Comparisons are made with Udacity's Introduction to Machine Learning.