I recently read Ferenc Huszár's blog post summarizing recent research on how evolutionary strategies can be used in place of gradient descent or back-propagation. That research focuses on how evolutionary strategies for reinforcement learning get the same results as back-propagation, but the computation is more parallelizable and therefore faster ...Continue reading
I've grown increasingly frustrated with the way the popular press talks about Machine Learning and Artificial Intelligence.
Too many articles talk about Machine Learning (ML) as a sci-fi black box capable of doing and learning anything, and leave the reader with a poorer understanding of what ML is than ...Continue reading
A self-lead refresher course in basic ML algorithms
I'm in the process of implementing various machine learning algorithms from scratch and will write a short series of blogs posts about this project. This first post will be about what motivated this project and a bit about what I've ...Continue reading
- Andrej Karpathy reminds you that "Yes you should understand backprop". For an intuitive and in-depth intro to backpropogation I recommend his convolutional neural network lectures.
- Bill Bryson - The Mother Tongue: English and How It Got That Way , an entertaining if sometimes undirected tour through the history of the English ...
Please don't try to read into this blog post any political beliefs or agenda. This is simply an exercise in conditional probabilities.
In case you're on the internet for the first time this year, this election has been... different. For example, there's talk about how GOP convention ...Continue reading
I'm trying out a new idea for blog posts - an occasional (monthly?) series on what I'm reading and what I'm eating.
- If the first 11 socks I pull out of the dryer all are distinct, how many total socks are in the dryer? Rasmus Baath explains ...
Note: this post doesn't describe original mathematical research on my part. My initial motivation to write this post was simply that I was surprised by how hard it was to find a formula for the confidence ...Continue reading