Lack of generalization != overfitting. Lack of generalization could come from overfitting, underfitting, concept drift, OOD, or could come up for a model where there's no "fitting" at all. It just means that the model cannot operate in situations it hasn't been prepared for
@fchollet
-
Limitations of Training AI Models on Synthetic and Video Data
By
–
But you can't just fit a big curve to a bunch of UE5 screencaps and YouTube videos and expect a generalizable model of the real world. That is not how these models work.
-
Large Curves: Weather Prediction and Simulator Applications
By
–
Could you use a big curve to predict the weather? Yes, given enormous amounts of data. We're already doing it! To make a wind chamber simulator? Yes, if you can keep as many parameters as possible fixed, and if you can densely sample training data for the parameters that do vary
-
ML Research and Applied ML Require Different Skill Sets
By
–
The skills needed for developing new ML techniques have little overlap with the skills needed for applying ML effectively. A bit like how chip design has little overlap with software engineering.
-
Keras Starter Notebook for Kaggle Brain Activity Classification
By
–
Are you doing the 'Harmful Brain Activity Classification' competition on Kaggle? Check out this neat Keras starter notebook:
-
AI Usage Does Not Provide the Writing Advantage Assumed
By
–
Using AI is not the unfair writing advantage you think it is.
-
LLMs Diminish Writing Quality: Practical Experience
By
–
Countless times, I've tried using LLMs to help with writing blog posts, book chapters, tweets. I've consistently found that it made my writing worse and was a waste of time. The most I ended up incorporating in a final product is one sentence in one blog post.
-
LLM Usage in Student Essays: Plagiarism Matters More Than Tool
By
–
My take: if an essay isn't plagiarized, then it's not that important whether it was written with the help of a LLM or not. If you're really worried about it, just have the students write the essays during class.
-
ML classifiers cannot reliably detect LLM-generated text
By
–
Remember: a ML classifier cannot reliably tell you whether some text was generated by a LLM or not. There are no surefire features, and spurious correlations abound. Besides, it's not ethically sound to punish someone based on a classification decision made by an algorithm with
-
Logical fallacy: Equating two misunderstood phenomena
By
–
Up there with "I don't understand consciousness; I don't understand quantum physics; therefore consciousness is quantum"