Tweetovi
- Tweetovi, trenutna stranica.
- Tweetovi i odgovori
- Medijski sadržaj
Blokirali ste korisnika/cu @kaixhin
Jeste li sigurni da želite vidjeti te tweetove? Time nećete deblokirati korisnika/cu @kaixhin
-
Prikvačeni tweet
A Brief Survey of Deep Reinforcement Learning w/
@mpd37 &@Miles_Brundage: https://arxiv.org/abs/1708.05866Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Kai Arulkumaran proslijedio/la je Tweet
François (
@madlag) is both an independent ML researcher investigating sparse efficient models and... an early angel investor in
Happy that he agreed to share some of his knowledge and experience on sparse models in a series of posts!
First one is herehttps://medium.com/huggingface/is-the-future-of-neural-networks-sparse-an-introduction-1-n-d03923ecbd70 …Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Just tried to do "From Zero to MuZero" in 30 minutes (zero = starting from RL) for my lab meeting! Ran through MDPs, RL loop, MB vs. MF RL, Bellman backups, MCTS, POMDPs, and then how MuZero combines these to learn a latent state to run AlphaZero style.
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
brb gonna write that sci-fi novel nowhttps://twitter.com/qikipedia/status/1223999517198077956 …
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Kai Arulkumaran proslijedio/la je Tweet
On Tuesday, in my class, we have learnt that all a neural net does is stretching / contracting the space fabric. For example this 3-layer net (1 hidden layer of 100 positive neurons) gets its 5D logits (2D projections) linearly separable by the classifier hyperplanes (lines).pic.twitter.com/PzVLDxBTNq
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Kai Arulkumaran proslijedio/la je Tweet
This is a great opportunity to get involved and support
#WiML. Apply to be an organizer or share with anyone who could be interested!https://twitter.com/WiMLworkshop/status/1223708634150031361 …Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Excited to see what
@CovariantAI has achieved, and there's more details about their approach here. Seems that scaling up and combining current methods (SL/IL/RL) in smart ways can go pretty far!https://twitter.com/BotJunkie/status/1222467251514892288 …Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Kai Arulkumaran proslijedio/la je Tweet
We're standardizing OpenAI's deep learning framework on PyTorch to increase our research productivity at scale on GPUs (and have just released a PyTorch version of Spinning Up in Deep RL): https://openai.com/blog/openai-pytorch/ …pic.twitter.com/lgvqDdWDoB
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Fantastic initiative from
@MSFTResearch combining a range of AI techniques to help blind/partially sighted people! Happy to have played a small role in the past.https://twitter.com/MSFTEnable/status/1222893892665610240 …Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Kai Arulkumaran proslijedio/la je Tweet
After 2+ years in stealth, we’re excited to launch today! https://covariant.ai Thank you to our team, customers, partners and investors, we couldn’t have done it w/o your support and trust. Exciting milestone, even more exciting journey ahead!https://medium.com/covariant-ai/bringing-robots-from-lab-to-the-real-world-56062ee93dd5 …
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Kai Arulkumaran proslijedio/la je Tweet
As someone who didn't go for it, this is a great view into the life of a phd student from
@kaixhin
. Love this in particular
Everyone has a different “work-life balance” (and for me, “work” is an essential part of my “life”)https://twitter.com/kaixhin/status/1222464085595500544 …Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
I did an interview with
@discoverphds about my work, my life, and my advice for PhDs. So please check it out if you'd like to find out about any of those
https://discoverphds.com/phd-advice-student-hub/phd-student-interviews/kai-arulkumaran-phd-student-interviews/ … #PhDChat#AcademicChatterHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Get you a model class that can approximate it all
#dollypartonchallengepic.twitter.com/jBp6TADfPH
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Is there a word for the feeling you get after watching a Makoto Shinkai film? Just saw Weathering With You, and feeling like that.
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
I was hoping to ask him what the reward function for AGI was, but someone basically beat me to it. David's response to "where do rewards come from?" was that he was concerned with solving specified problems, and left that question to other people.
Prikaži ovu nitHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
David Silver's "provocative" slide. A "conjecture" that this might take us towards the goal of AGI (but not the "hubris" that this is definitely the way to go).pic.twitter.com/uhvRdEoYCl
Prikaži ovu nitHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Kai Arulkumaran proslijedio/la je Tweet
You got a bunch of GPU machines and are wondering which GPUs are still free? I used to ssh into the list of machines and checked manually until I built a small dashboard to show me: https://github.com/pawni/gpuobserver … I thought other people might have the same problem..pic.twitter.com/WQBzVFQbs2
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Kai Arulkumaran proslijedio/la je Tweet
Differentiable Digital Signal Processing (DDSP)! Fusing classic interpretable DSP with neural networks.
Blog: http://magenta.tensorflow.org/ddsp
Examples: https://g.co/magenta/ddsp-examples …
Colab: http://g.co/magenta/ddsp-demo …
Code: http://github.com/magenta/ddsp
Paper: http://g.co/magenta/ddsp-paper …
1/pic.twitter.com/SlxLUOUC6k
Prikaži ovu nitHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Kai Arulkumaran proslijedio/la je Tweet
v1.4: customizable mobile builds, Distributed Model Parallelism via experimental RPC API, Java Bindings, Chaining LRSchedulers Summary: https://pytorch.org/blog/pytorch-1-dot-4-released-and-domain-libraries-updated/ … Release Notes: https://github.com/pytorch/pytorch/releases/tag/v1.4.0 … Last release for Python 2 (bye bye!)
Prikaži ovu nitHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Kai Arulkumaran proslijedio/la je Tweet
Introducing computer-designed organisms. Our new study out this week in PNAS. w/
@drmichaellevin, Douglas Blackiston, and@Kriegmericapic.twitter.com/qBjeqMkFBAPrikaži ovu nitHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Kai Arulkumaran proslijedio/la je Tweet
I often meet research scientists interested in open-sourcing their code/research and asking for advice. Here is a thread for you. First: why should you open-source models along with your paper? Because science is a virtuous circle of knowledge sharing not a zero-sum competitionpic.twitter.com/x16jgKmLFr
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.