U tweetove putem weba ili aplikacija drugih proizvođača možete dodati podatke o lokaciji, kao što su grad ili točna lokacija. Povijest lokacija tweetova uvijek možete izbrisati. Saznajte više
The "Deep Learning Toolbox" has greatly expanded in the last decade thanks to our wonderful research community. Also, important progress has been made to make our community more inclusive and less toxic. Still, there's LOTS to do, and I plan to keep focusing on advancing both.pic.twitter.com/C5r4wDGSN9
The figure above is an (old) slide I usually show in lectures and talks. Mix and matching those components creates cool architectures such as the one used in #OpenAIFive or #AlphaStar.pic.twitter.com/6udLczZUXj
is more of the deck available?
I've used this in several lectures, but perhaps the NeurIPS 2017 tutorial is a good one: http://goo.gl/b6QBBh (context: https://twitter.com/OriolVinyalsML/status/937441237728034816 …)
Can I ask how the switch from image-based observations to object-level descriptions came about? My own work has been focusing on the advantages of object-level representation and how to use them, so it would be good to hear what the DeepMind experience was.
We tried both and found object based to be superior earlier in the project. You can see an interesting work on using an interesting mixture here: https://arxiv.org/abs/1806.01830
Twitter je možda preopterećen ili ima kratkotrajnih poteškoća u radu. Pokušajte ponovno ili potražite dodatne informacije u odjeljku Status Twittera.
