Matteo Risso
@mattrix96.bsky.social
CS PhD Student in Italy 🇮🇹
Working towards making Deep Learning at-the-edge feasible.
🐱 GitHub: https://github.com/matteorisso
🎓 Scholar: https://scholar.google.com/citations?user=ltE9im8AAAAJ&hl=en
🕸️🏗️ matteorisso.github.io
Working towards making Deep Learning at-the-edge feasible.
🐱 GitHub: https://github.com/matteorisso
🎓 Scholar: https://scholar.google.com/citations?user=ltE9im8AAAAJ&hl=en
🕸️🏗️ matteorisso.github.io
I used it for a keyword spotting task. Well, it is actually the sota (not by me) as far as I know. I’m using a model trained in such way to explore some particular compression techniques.
Anyway, I’d love to hear more :)
Anyway, I’d love to hear more :)
November 30, 2024 at 8:24 PM
I used it for a keyword spotting task. Well, it is actually the sota (not by me) as far as I know. I’m using a model trained in such way to explore some particular compression techniques.
Anyway, I’d love to hear more :)
Anyway, I’d love to hear more :)
I mean, I think your posts are really useful, so if you can maximize their spread I think everyone would benefit :)
November 29, 2024 at 5:25 PM
I mean, I think your posts are really useful, so if you can maximize their spread I think everyone would benefit :)
Hi Michael, I enjoy a lot your photos! Especially the ones with the dog in the nature :)
November 26, 2024 at 8:46 PM
Hi Michael, I enjoy a lot your photos! Especially the ones with the dog in the nature :)
Yes, you’re definitely right. The fact is that without the proper attitude it becomes overwhelming or you starting jumping around too many things. Nonetheless, I like the positivity you are spreading, tomorrow I will have some time and I will make it worth ;)
November 23, 2024 at 9:41 PM
Yes, you’re definitely right. The fact is that without the proper attitude it becomes overwhelming or you starting jumping around too many things. Nonetheless, I like the positivity you are spreading, tomorrow I will have some time and I will make it worth ;)
The problem is finding the time for all these nice things :( everyday I fall in love with something new
November 23, 2024 at 9:35 PM
The problem is finding the time for all these nice things :( everyday I fall in love with something new
Would love to join
November 23, 2024 at 9:00 PM
Would love to join
Oh, that’s really nice to hear! I was thinking it was a work meant to be closed source. I’ll wait patiently then
November 22, 2024 at 10:00 PM
Oh, that’s really nice to hear! I was thinking it was a work meant to be closed source. I’ll wait patiently then
Interesting! I would love to know more but I suppose you already said what you could ;)
November 22, 2024 at 9:56 PM
Interesting! I would love to know more but I suppose you already said what you could ;)
Really nice work! Looking forward for the next updates!
Btw, is the model something new or did you “simply” scaled down a well know architecture ?
Btw, is the model something new or did you “simply” scaled down a well know architecture ?
November 22, 2024 at 9:51 PM
Really nice work! Looking forward for the next updates!
Btw, is the model something new or did you “simply” scaled down a well know architecture ?
Btw, is the model something new or did you “simply” scaled down a well know architecture ?
Honestly my X feed was good enough but many people that I love to interact with moved so I did it
November 20, 2024 at 1:59 PM
Honestly my X feed was good enough but many people that I love to interact with moved so I did it
Farfalline rimandate sul nucleare :(
November 20, 2024 at 1:12 PM
Farfalline rimandate sul nucleare :(
Omg this is so me!
November 20, 2024 at 11:48 AM
Omg this is so me!
P.S., I can definetely wrong on some details, not an expert in GPU arch :)
November 20, 2024 at 9:24 AM
P.S., I can definetely wrong on some details, not an expert in GPU arch :)
Apple GPU cores should corresponds to the Streaming Multiprocessors (SM) of NVIDIA.
In the Lovelace architecture each should be composed of 128 CUDA cores which are “composed” of a warp of 32 threads…
I think it depends what you want to compare. For raw compute you can compare num of threads
In the Lovelace architecture each should be composed of 128 CUDA cores which are “composed” of a warp of 32 threads…
I think it depends what you want to compare. For raw compute you can compare num of threads
November 20, 2024 at 9:23 AM
Apple GPU cores should corresponds to the Streaming Multiprocessors (SM) of NVIDIA.
In the Lovelace architecture each should be composed of 128 CUDA cores which are “composed” of a warp of 32 threads…
I think it depends what you want to compare. For raw compute you can compare num of threads
In the Lovelace architecture each should be composed of 128 CUDA cores which are “composed” of a warp of 32 threads…
I think it depends what you want to compare. For raw compute you can compare num of threads
Really interesting, thx!
November 19, 2024 at 12:30 PM
Really interesting, thx!
Would love to be added! I did some work with EMG and PPG!
November 19, 2024 at 7:11 AM
Would love to be added! I did some work with EMG and PPG!
I didn’t think a lot about it, but everything here on bluesky is much more immediate than on mastodon.
November 18, 2024 at 9:38 PM
I didn’t think a lot about it, but everything here on bluesky is much more immediate than on mastodon.
In the future I would love to find the time to explore the resiliency of such models to optimization (which is really my field of expertise) such as quantization, pruning, etc. in order to explore the feasibility of deploying them directly on satellite HW
November 18, 2024 at 9:29 PM
In the future I would love to find the time to explore the resiliency of such models to optimization (which is really my field of expertise) such as quantization, pruning, etc. in order to explore the feasibility of deploying them directly on satellite HW