If someone likes programming in Rust, how would Mojo help here?
@rasbt
-
Computing Fragmentation Creates Barriers for Deep Learning Education
By
–
Sure, but a lot of people don’t have that kind of time. If the computing ecosystem would be that fragmented, the prerequisites for a intro to deep learning class would be insane
-
Transformers Are Popular But Simple Baselines Still Matter
By
–
Yeah. I doubt that there will be a follow-up paper though. I think the point was more like "transformers are the shiny new toy, but don't forget about also implementing simple baselines when you start a new project".
-
Disclosure Differences Between LLMs and BERT Models
By
–
Interesting point. For LLMs like GPT-3 & 4 we simply don't know because it's not disclosed. For BERT we do know though. There's separate BERT-English and BERT-multilingual models, for example, etc.
-
Gzip and kNN: Text Similarity Through Compression
By
–
In short, the idea behind this gzip + kNN approach is that a given text A is close to the size of two concatenated texts A + B when compressed using Gzip. Or, the compressed size of A+A is similar to the compressed size of just A (plus a constant value for the back reference)
-
Sequence Packing Applied to Image Patches – Novel Approach
By
–
So, basically sequence packing but for image patches. Neat. And surprised no one has tried that yet
-
Changing Opinion After Reading a Research Paper
By
–
No I first was and then I wasn’t when I saw that paper and all the congrats in the replies . (How do we expect LLMs to ever solve text comprehension)
-
Congratulations on Real XAI Research Work
By
–
Haha I am just realizing that you are working on real XAI, not xAI)! In that case, real non-sarcastic congrats!! We need more of this!
-
KNN Classification Works Through Majority Vote Among Neighbors
By
–
Yes, I assume this should work because the compute the label based on majority vote among the nearest neighbors.
-
Nearest-Neighbor Approach on Normalized Bag-of-Words Vectors
By
–
Thinking about this a bit more, I think nearest-neighbor on normalized bag-of-words vectors would probably also perform well here. Because the count vectors of two similar documents are similar just like the compressed + concatenated compressed docs are similar.