Tweetovi
- Tweetovi, trenutna stranica.
- Tweetovi i odgovori
- Medijski sadržaj
Blokirali ste korisnika/cu @rmpnegrinho
Jeste li sigurni da želite vidjeti te tweetove? Time nećete deblokirati korisnika/cu @rmpnegrinho
-
Prikvačeni tweet
I'm thrilled to finally announce the release of DeepArchitect, a modular and programmable architecture search framework that you can actually use for your use cases. This work has been accepted at
#NeurIPS2019. Preprint: https://arxiv.org/abs/1909.13404 (see thread)Prikaži ovu nitHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi
-
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi
-
Hate how you constantly misrepresent our community's understanding of the limitations of current methods. Please submit your papers with concrete solutions to next year's NeurIPS. 2/2
Prikaži ovu nitHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
I'm attending at NeurIPS this week. Reach out if you want to chat. Our poster presentation is on Thursday 10:45-12:45, East Exhibition Hall B + C #36, so definitely stop by then.
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Wrote a blog post with a collection of tips and references for writing academic papers. These are things that I learned over the years. Still trying to improve.http://bit.ly/2Rk4m7g
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Renato Negrinho proslijedio/la je Tweet
Here's Richard Feynman, in 1985, describing Douglas Lenat's heuristic-based system and its winning solutions. Reminds me of reinforcement learning efforts of today. Given objectives & constraints, algorithms may lead to unexpected consequences. Full clip: https://www.youtube.com/watch?v=ipRvjS7q1DI …pic.twitter.com/CwiVwF3u5T
Prikaži ovu nitHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Created a Google Colab to easily play with DeepArchitect and run the examples in the paper, blog post, and repo readme. Check it out: https://colab.research.google.com/drive/14xZdGB-BbIivdgNje3Gu7ZmK0m4F02kE … .
Prikaži ovu nitHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Just found http://matt.might.net/articles . The graduate section should be required reading for PhD students and advisors alike.
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
CC'ing some relevant handles:
@quocleix@h2oai@weights_biasesPrikaži ovu nitHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Reach out if you want to get involved (e.g., by implementing existing search spaces or search algorithms; or extending the framework somehow). I'll be maintaining the framework. Plenty of references to resources can be found here: https://github.com/negrinho/deep_architect … . Feedback appreciated.
Prikaži ovu nitHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
This implementation addresses many of the limitations of the initial prototype here: https://github.com/negrinho/deep_architect_legacy … Supports multi-input multi-output modules, hyperparameter sharing, and multiple frameworks.
Prikaži ovu nitHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
The language relies on notions of lazy evaluation, e.g., we might know that we want an encoder, but only after choosing values for all the hyperparameters, we will have a concrete encoder. Nonetheless, until then, we still have sub-graph that we can refer to.
Prikaži ovu nitHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Crucially, compared to hyperparameter optimization, you don't have to write separately the encoding of hyperparameter space and the mapping from instances in the space to their implementations. In our language, the mapping is created automatically from the encoding.
Prikaži ovu nitHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
In our implementation, see these search space transitions (http://bit.ly/2p6v3k0 ) for an example search space (search_space_5; http://bit.ly/2nzfsZO ). A more complex example here (http://bit.ly/2mGUl7l ) for the search space here (http://bit.ly/2oknkP2 ).
Prikaži ovu nitHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
If you only want to get a gist, our search space example section in the paper is a good reference (see images).pic.twitter.com/fPBUZ20Sk4
Prikaži ovu nitHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
This language allows us to decouple the implementations of search spaces and search algorithms to a large extent. This allow architecture search code to be more widely used and reused in the literature. See documentation for more information.
Prikaži ovu nitHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
We design the language to encode search spaces over computational graphs (e.g., deep learning architectures). We often have good inductive biases about what ops are useful, but don't know exact sequence + hyperps. Our language gives us constructs to express design uncertainty.
Prikaži ovu nitHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
It is extensible to any domain for which it makes sense to do architecture search, but currently supports Tensorflow, Keras, and Pytorch. Easy to add support for new domains. Code: https://github.com/negrinho/deep_architect … Documentation: https://deep-architect.readthedocs.io/en/latest/ Examples:https://github.com/negrinho/deep_architect/tree/master/examples …
Prikaži ovu nitHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
server workflow: https://negrinho.github.io/2019/05/26/server-workflow.html … NYT notes: https://negrinho.github.io/2019/06/12/nyt-chat-about-automl.html … NeurIPS 2019: - Paper: https://arxiv.org/abs/1909.13404 - Code: https://github.com/negrinho/deep_architect … - Documentation: https://deep-architect.readthedocs.io/en/latest/ - Blog: https://negrinho.github.io/2019/07/26/introducing-deep-architect.html … I will announce the paper properly soon.
Prikaži ovu nitHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi
Čini se da učitavanje traje već neko vrijeme.
Twitter je možda preopterećen ili ima kratkotrajnih poteškoća u radu. Pokušajte ponovno ili potražite dodatne informacije u odjeljku Status Twittera.