In this video upload available on Spotify (we’ll try this once and see how it’s received), we revisit Reinforcement Learning (from way back in episode…
Category: Machine Learning
I previously posted about Deutsch’s argument to Eli Tyre about why induction can’t be the basis for conjecture. And I agreed with that argument. But,…
In this episode, we review Alpha Go: The Movie. This is an amazing documentary worth watching before we spoil it for you in this review.…
Reinforcement Learning is a machine learning algorithm that is a ‘general purpose learner’ (with certain important caveats). It generated a lot of excitement with its…
“Reinforcement Learning with Augmented Data,” (link) by Michael Laskin, et al introduces the idea of using data augmentation in Reinforcement Learning. Data augmentation is already…
I was already signed up for Computer Vision when word came that there would be a new Deep Learning class next semester. I quickly got…
Despite appearances, this post isn’t intended as a political post. I simply utilized the example that led to the thought that inspired the post. We…
Bruce and I have an ongoing discussion about our differing interpretation of Donald Campbell’s notion of “blindness”. Bruce has previously published a post explaining his…
“ImageNet-Trained CNNs are Biased Towards Texture; Increasing Shape Bias Improves Accuracy and Robustness” (link) by Robert Geirhos, et al explores two proposed theories about how…
“Language Models are Few-Shot Learners” by Brown, et al (link) was the world’s introduction to Open AI’s GPT-3, the state of the art language model…