For me at least it’s partly that the need isn’t as great now as in 2013 when we planned v1. Deep Learning has gone from a niche academic workshop topic to the most publicized product of more than one > trillion dollar company.
@goodfellow_ian
-
Why Deep Learning Textbook Lacks Code Examples
By
–
Sometimes people ask me why there isn’t code in the Deep Learning textbook and I say “well, the code would’ve been in pylearn2,” and they say “what’s pylearn2?” and I say “exactly.”
-
Theano and cuda-convnet: Early deep learning frameworks history
By
–
Yoshua’s lab was all Theano. I actually wrote Theano bindings for Alex’s cuda-convnet before ImageNet came out. He was working on the code as an open source library and had good results on CIFAR quite a while before the ImageNet results were public.
-
Data Representations Foundation Machine Learning Computer Science
By
–
In chapter 1 of http://
deeplearningbook.org we say that data representations are crucial for not just machine learning or even computer science but daily life (e.g. try dividing numbers by hand with Roman numerals). -
Startups Share Technical Stack Details for LLM Implementation
By
–
Startups usually don’t say a lot about how their stack works (or it’s just a wrapper around another company’s LLM) so it’s great to get this detailed deep dive
-
Management misconception about development difficulty
By
–
If the manager thinks “have got something working” is the hard/slow part, well, there’s the problem
-
Scheduled Sampling Technique in AI Model Training
By
–
This is somewhat similar to scheduled sampling, right?
-
Friend launches GAN project for home GPU testing
By
–
Exciting news from my friend and GAN co-author, I’m looking forward to trying this out on my own GPU at home
-
ML Security: Closing the Gap Between Capabilities and Robustness
By
–
I've spent several years studying machine learning security with the goal of making ML reliable before it is used in more and more important contexts. Unfortunately, ML capabilities and adoption are growing much faster than ML robustness.