That site hijacks the CMD+LEFT and CMD+RIGHT Mac hotkeys for browser BACK/FORWARD and also has very strange behavior when scrolling with the keyboard. Why? Why? Why?
Lessons from a year of AI research
11–20 of 48 posts
Re: Lessons from a year of AI research
#12That site hijacks the CMD+LEFT and CMD+RIGHT Mac hotkeys for browser BACK/FORWARD and also has very strange behavior when scrolling with the keyboard. Why? Why? Why?
This seems really like a browser problem, and I'd love to know a fix. Geogebra.org hijacks CMD-` in Safari and it is absolutely infuriating.
Re: Lessons from a year of AI research
#13The one that matters is missing: how do you get the best random seeds? /s
# Sussman attains enlightenment
In the days when Sussman was a novice, Minsky once came to him as he sat hacking at the PDP-6.
“What are you doing?”, asked Minsky. “I am training a randomly wired neural net to play Tic-Tac-Toe” Sussman replied.
“Why is the net wired randomly?”, asked Minsky. “I do not want it to have any preconceptions of how to play”, Sussman said.
Minsky then shut his eyes.
“Why do you close your eyes?”, Sussman asked his teacher. “So that the room will be empty.”
At that moment, Sussman was enlightened.
Re: Lessons from a year of AI research
#14The one that matters is missing: how do you get the best random seeds? /s
# Sussman attains enlightenment In the days when Sussman was a novice, Minsky once came to him as he sat hacking at the PDP-6. “What are you doing?”, asked Minsky. “I am training a randomly wired neural net to play Tic-Tac-Toe” Sussman replied. “Why is the net wired randomly?”, asked Minsky. “I do not want it to have any preconceptions of how to play”, Sussman said. Minsky then shut his eyes. “Why do you close your e…
I'm not actually sure what the morale is here
Re: Lessons from a year of AI research
#15Earlier quoted context omitted.
# Sussman attains enlightenment In the days when Sussman was a novice, Minsky once came to him as he sat hacking at the PDP-6. “What are you doing?”, asked Minsky. “I am training a randomly wired neural net to play Tic-Tac-Toe” Sussman replied. “Why is the net wired randomly?”, asked Minsky. “I do not want it to have any preconceptions of how to play”, Sussman said. Minsky then shut his eyes. “Why do you close your e…
I'm not actually sure what the morale is here
Intelligence does not start from a random state, but from a pretrained one. Random state is likely to roll an artificial overfit or if it just fits, you won't know why it is better than another state - or rather why your training method sucks from other initial states.
Proper methods of bias analysis are network compression or random surgery, and expanding test data set. Proper methods of training are robust to varied initial states.
Re: Lessons from a year of AI research
#16Earlier quoted context omitted.
# Sussman attains enlightenment In the days when Sussman was a novice, Minsky once came to him as he sat hacking at the PDP-6. “What are you doing?”, asked Minsky. “I am training a randomly wired neural net to play Tic-Tac-Toe” Sussman replied. “Why is the net wired randomly?”, asked Minsky. “I do not want it to have any preconceptions of how to play”, Sussman said. Minsky then shut his eyes. “Why do you close your e…
I'm not actually sure what the morale is here
If you shut your eyes, you do not see anything in the room. This does not mean there is nothing in the room.
If you randomize your seeds, you do not deliberately bias your model. This does not mean your model is unbiased.
Re: Lessons from a year of AI research
#17The author might find that this well thought out list will help when applying for work. I would suggest that they copy it over to GitHub in addition to their public projects.
Re: Lessons from a year of AI research
#18101st lesson - 100 is a nice number but no one is going to read a blog post with 100 lessons learned. Either focus on the 5-10 most important lessons or consolidate and summarize.
Re: Lessons from a year of AI research
#19Good list! As a PhD student and therefore AI researcher for a few years now, a lot of this rings true. Though 100 lessons is too much and some of these are obvious/minor, i'd distill it down to the main ones.
Here's my 2 cents on the topic from a thing I wrote last year ('Lessons Learned the Hard Way in Grad School (so far)'): https://www.andreykurenkov.com/writing/life/lessons-learned-...
Re: Lessons from a year of AI research
#20The title here and on the blog differs, I don't know why submiters pick other titles. I mean I wouldn't quote a newspaper or paper with a wrong title, would I?
It is one of the site's guidelines.
>If the title contains a gratuitous number or number + adjective, we'd appreciate it if you'd crop it. E.g. translate "10 Ways To Do X" to "How To Do X," and "14 Amazing Ys" to "Ys." Exception: when the number is meaningful, e.g. "The 5 Platonic Solids."