Davide Eynard
@aittalam.bsky.social
Dad of 3564020356.org, PicoGopher, and two amazing kids. Interested in open applications of ML on federated systems. Trustworthy AI at mozilla.ai. Genetically a teacher, forever a student. He/him.
@mala@fosstodon.org
@mala@fosstodon.org
... small AI and some of its principles including:
- if you don't need it, don't use it 🙂
- own your algorithms
- run them on your hardware
- use them to serve *your* needs
@kathleenchu.bsky.social has been a great host and I ❤️ her work, which I suggest you to check out regardless of my AI rants 😉
- if you don't need it, don't use it 🙂
- own your algorithms
- run them on your hardware
- use them to serve *your* needs
@kathleenchu.bsky.social has been a great host and I ❤️ her work, which I suggest you to check out regardless of my AI rants 😉
April 28, 2025 at 3:34 PM
... small AI and some of its principles including:
- if you don't need it, don't use it 🙂
- own your algorithms
- run them on your hardware
- use them to serve *your* needs
@kathleenchu.bsky.social has been a great host and I ❤️ her work, which I suggest you to check out regardless of my AI rants 😉
- if you don't need it, don't use it 🙂
- own your algorithms
- run them on your hardware
- use them to serve *your* needs
@kathleenchu.bsky.social has been a great host and I ❤️ her work, which I suggest you to check out regardless of my AI rants 😉
Oh yes, then custom bayes classifiers (I think there's a reference in Vicki's link) are definitely a fun thing to play with!
Another thing I'd find interesting are efficient built-in binary set operators (e.g. re-ranking via dot product, set similarity... Even mapping might be seen as a set op? 🤔)
Another thing I'd find interesting are efficient built-in binary set operators (e.g. re-ranking via dot product, set similarity... Even mapping might be seen as a set op? 🤔)
April 9, 2025 at 5:13 PM
Oh yes, then custom bayes classifiers (I think there's a reference in Vicki's link) are definitely a fun thing to play with!
Another thing I'd find interesting are efficient built-in binary set operators (e.g. re-ranking via dot product, set similarity... Even mapping might be seen as a set op? 🤔)
Another thing I'd find interesting are efficient built-in binary set operators (e.g. re-ranking via dot product, set similarity... Even mapping might be seen as a set op? 🤔)
… if you want you can train a small MLP on top of them. Yeah I know this boils back to the learned embedding case you were trying to move from… But if you learn them yourself it’s more fun 🙂
April 9, 2025 at 7:52 AM
… if you want you can train a small MLP on top of them. Yeah I know this boils back to the learned embedding case you were trying to move from… But if you learn them yourself it’s more fun 🙂
If you are not constrained to NLP there’s a lot you can play with in CV (eg descriptors such as SIFT, HoG etc). Handcrafted (especially visual!) descriptors are easily interpretable + relatively cheap to calculate, still quite limited for ad-hoc tasks but…
April 9, 2025 at 7:52 AM
If you are not constrained to NLP there’s a lot you can play with in CV (eg descriptors such as SIFT, HoG etc). Handcrafted (especially visual!) descriptors are easily interpretable + relatively cheap to calculate, still quite limited for ad-hoc tasks but…
The demo is not local (which is what BYOTA is all about!), but I hope the message is still clear: we *can* run useful TL algorithms locally, without sharing our own data. We don’t need a lot of data and compute, if our goal is not to convince people to spend more time on a given platform.
March 22, 2025 at 11:33 AM
The demo is not local (which is what BYOTA is all about!), but I hope the message is still clear: we *can* run useful TL algorithms locally, without sharing our own data. We don’t need a lot of data and compute, if our goal is not to convince people to spend more time on a given platform.