Customer Predict
🚀
1
This project about Customer Prediction in Turkiye
🤝 Open to Collab
Fendy Hendriyanto
fendy07
·
AI & ML interests
Computer Vision and Natural Language Processing
Recent Activity
updated a Space 2 days ago
fendy07/customer-predict liked a model about 2 months ago
google/embeddinggemma-300m liked a dataset 5 months ago
indonlp/NusaX-MTOrganizations
None yet
updated a
Space 2 days ago
liked a
model about 2 months ago
liked a
dataset 5 months ago
liked a
model 6 months ago
liked a
dataset 6 months ago
updated a
Space 7 months ago
upvoted an article 7 months ago
Article
Qwen Image Edit 2511 Free and Open Source Crushes Qwen Image Edit 2509 and Challenges Nano Banana Pro
MonsterMMORPG
• • 2 liked 2
Spaces 7 months ago
published 2
Spaces 7 months ago
upvoted a collection about 1 year ago
liked a
dataset about 1 year ago
reacted to Sentdex's post with 🔥 about 2 years ago
Post
10665
Okay, first pass over KAN: Kolmogorov–Arnold Networks, it looks very interesting!
Interpretability of KAN model:
May be considered mostly as a safety issue these days, but it can also be used as a form of interaction between the user and a model, as this paper argues and I think they make a valid point here. With MLP, we only interact with the outputs, but KAN is an entirely different paradigm and I find it compelling.
Scalability:
KAN shows better parameter efficiency than MLP. This likely translates also to needing less data. We're already at the point with the frontier LLMs where all the data available from the internet is used + more is made synthetically...so we kind of need something better.
Continual learning:
KAN can handle new input information w/o catastrophic forgetting, which helps to keep a model up to date without relying on some database or retraining.
Sequential data:
This is probably what most people are curious about right now, and KANs are not shown to work with sequential data yet and it's unclear what the best approach might be to make it work well both in training and regarding the interpretability aspect. That said, there's a rich long history of achieving sequential data in variety of ways, so I don't think getting the ball rolling here would be too challenging.
Mostly, I just love a new paradigm and I want to see more!
KAN: Kolmogorov-Arnold Networks (2404.19756)
Interpretability of KAN model:
May be considered mostly as a safety issue these days, but it can also be used as a form of interaction between the user and a model, as this paper argues and I think they make a valid point here. With MLP, we only interact with the outputs, but KAN is an entirely different paradigm and I find it compelling.
Scalability:
KAN shows better parameter efficiency than MLP. This likely translates also to needing less data. We're already at the point with the frontier LLMs where all the data available from the internet is used + more is made synthetically...so we kind of need something better.
Continual learning:
KAN can handle new input information w/o catastrophic forgetting, which helps to keep a model up to date without relying on some database or retraining.
Sequential data:
This is probably what most people are curious about right now, and KANs are not shown to work with sequential data yet and it's unclear what the best approach might be to make it work well both in training and regarding the interpretability aspect. That said, there's a rich long history of achieving sequential data in variety of ways, so I don't think getting the ball rolling here would be too challenging.
Mostly, I just love a new paradigm and I want to see more!
KAN: Kolmogorov-Arnold Networks (2404.19756)
- 5 replies