All Posts
-
Link: Illustrative example (from radiology) why data quality and domain expertise is important
Spotted this on Twitter:
Luke Oakden-Rayner is a PhD candidate / radiologist, and he took a look at ChestXRay14, X-ray dataset used to train ML models for radiological image analysis. He believes the label quality in this particular dataset is not good enough for training ML systems for medical diagnosis.
Some key quotes below:
-
Link + Notes: Statistical Crisis in Science (Gelman @ Columbia)
YouTube link: The Statistical Crisis in Science and How to Move Forward by Professor Andrew Gelman (57 min; if you want to skip the introductions, the lecture starts at 5:30. Questions starting from 46:10).
-
Link: Fun image scatterplot visualization
-
Link: Kid-reviewed science journal
What a fun idea: Frontiers for Young Minds is a kid-reviewed science journal.
Or as they themselves say,
Frontiers for Young Minds provides a collection of freely available scientific articles by distinguished scientists that are shaped for younger audiences by the input of their own young peers.
-
Link: Five Ways to Fix Statistics
“Five Ways to Fix Statistics”, comment feature in Nature.
As debate rumbles on about how and how much poor statistics is to blame for poor reproducibility, Nature asked influential statisticians to recommend one change to improve science. The common theme? The problem is not our maths, but ourselves.
Summary of positions in the feature below (as far as I can discern):
-
Link: Annealing and Ensembling RMNIST
-
Link: Chidambaram On Research Statements
Short post: Advice on writing research statements, tweetstorm by Vijay Chidambaram:
-
Link (+ scattered notes): Impossibility of Intelligence Explosion
As you might’ve have already noticed, I think Francois Chollet (most famous as an author of Keras) is quite interesting person.
In a recent blogpost titled Impossibility of Intelligence Explosion (found via Juho Vaiste on Twitter and HN) he argues against the notion of singularity.
-
Links/Papers: Word2Vec + History + Stuff
Another topic of today: Word2Vec and predecessors.
This post belongs to ‘notes.to_self’ category; it contains less commentary and more links.
-
Link/Paper: Feature Visualization + Notes
Okay, let’s try to get started with this idea of topic-based-links-posting.
First thing I read today: an article about feature visualization in (deep) neural nets aka. Deep Dreaming.
The key reference I happened to read today is:
Olah, et al., “Feature Visualization”, Distill, 2017. Linky.