Tweetovi

	Connor Shorten proslijedio/la je tweet
	Alexey Kurakin @alexey2004	12 h
	Fixmatch: code for training on Imagenet dataset is released and available here: github.com/google-researc… arxiv.org/abs/2001.07685 by Kihyuk Sohn @D_Berthelot_ML @chunliang_tw @ZizhaoZhang Nicholas Carlini @ekindogus @alexey2004 @Han_Zhang_ @colinraffel
	Prikaz sažetka ·

	Connor Shorten proslijedio/la je tweet
	Lilian Weng @lilianweng	13 h
	Odgovor korisniku/ci @lilianweng I just realized that I missed another category of curriculum learning methods, so I added it in. Now the overview figure looks like this: pic.twitter.com/xofFlKMZfO
	Prikaz razgovora ·

	Connor Shorten proslijedio/la je tweet
	Connor Shorten @CShorten30	19 h
	This video explores Teacher-Student Curriculum Learning! Interestingly, the Teacher is rewarded for the Student's progress on Sub-Tasks rather than solely optimizing for progress on the hardest task, Intrinsic Motivation! youtu.be/GFCujBpTf3k #100DaysOfMLCode
	Prikaži podatke ·

	Connor Shorten @CShorten30	19 h
	This video explores Teacher-Student Curriculum Learning! Interestingly, the Teacher is rewarded for the Student's progress on Sub-Tasks rather than solely optimizing for progress on the hardest task, Intrinsic Motivation! youtu.be/GFCujBpTf3k #100DaysOfMLCode
	Prikaži podatke ·

	Connor Shorten @CShorten30	22 h
	Odgovor korisniku/ci @kaixhin Maybe you will find this video I made useful, titled: "The Evolution of AlphaGo to MuZero"! youtube.com/watch?v=A0HX8B…
	Prikaz razgovora ·

	Connor Shorten proslijedio/la je tweet
	Connor Shorten @CShorten30	4. velj
	This video explores "Learning to Execute" using Sequence-to-Sequence LSTMs to predict the output of a Python program without running the code! I was really interested in this paper because of their exploration into Curriculum Learning! youtu.be/5rrldwJdDRE #100DaysOfMLCode
	Prikaži podatke ·

	Connor Shorten @CShorten30	4. velj
	This video explores "Learning to Execute" using Sequence-to-Sequence LSTMs to predict the output of a Python program without running the code! I was really interested in this paper because of their exploration into Curriculum Learning! youtu.be/5rrldwJdDRE #100DaysOfMLCode
	Prikaži podatke ·

	Connor Shorten proslijedio/la je tweet
	Connor Shorten @CShorten30	3. velj
	AI Weekly update for February 3rd, 2020! This update covers Google AI's Meena Chatbot, Microsoft's ImageBERT, blog posts on Curriculum Learning in RL and Contrastive Self-Supervised Learning, and more! youtu.be/N9jsScucOXs #100DaysOfMLCode
	Prikaži podatke ·

	Connor Shorten @CShorten30	3. velj
	AI Weekly update for February 3rd, 2020! This update covers Google AI's Meena Chatbot, Microsoft's ImageBERT, blog posts on Curriculum Learning in RL and Contrastive Self-Supervised Learning, and more! youtu.be/N9jsScucOXs #100DaysOfMLCode
	Prikaži podatke ·

	Connor Shorten @CShorten30	3. velj
	Odgovor korisniku/ci @Deep_In_Depth Thanks for sharing!
	Prikaz razgovora ·

	Connor Shorten proslijedio/la je tweet
	Sebastian Ruder @seb_ruder	1. velj
	Curriculum for Reinforcement Learning "Learning is probably the best superpower we humans have." @lilianweng explores four types of curricula that have been used to help RL models learn to solve complicated tasks. lilianweng.github.io/lil-log/2020/0… pic.twitter.com/UTWHt9l3ng
	Prikaz fotografije ·

	Connor Shorten @CShorten30	31. sij
	I highly recommend checking out the lecture series from "Full Stack Deep Learning" on YouTube youtube.com/watch?v=5ygO8F… #100DaysOfMLCode
	Prikaži podatke ·

	Connor Shorten @CShorten30	31. sij
	Odgovor korisniku/ci @D_Berthelot_ML Thanks for sharing!!
	Prikaz razgovora ·

	Connor Shorten proslijedio/la je tweet
	David Berthelot @D_Berthelot_ML	31. sij
	A well done video explanation of FixMatch, thanks @CShorten30 ! twitter.com/CShorten30/sta…
	Prikaži podatke ·

	Connor Shorten @CShorten30	30. sij
	Thank you for sharing!! Great work on this paper! twitter.com/lmthang/status…
	Prikaži podatke ·

	Connor Shorten @CShorten30	29. sij
	Thank you!! Really enjoyed reading this paper! The relationship between BPE and the Hayvard joke is amazing! twitter.com/EdwardDixon3/s…
	Prikaži podatke ·

	Connor Shorten proslijedio/la je tweet
	Connor Shorten @CShorten30	29. sij
	This video explains @GoogleAI 's amazing new Meena chatbot! An Evolved Transformer with 2.6B parameters on 341 GB / 40B words of conversation data to achieves remarkable chatbot performance! "Horses go to Hayvard!" youtu.be/STrrlLG15OY #100DaysOfMLCode
	Prikaži podatke ·

	Connor Shorten @CShorten30	29. sij
	This video explains @GoogleAI 's amazing new Meena chatbot! An Evolved Transformer with 2.6B parameters on 341 GB / 40B words of conversation data to achieves remarkable chatbot performance! "Horses go to Hayvard!" youtu.be/STrrlLG15OY #100DaysOfMLCode
	Prikaži podatke ·

	Connor Shorten @CShorten30	29. sij
	Odgovor korisniku/ci @NTDeterminestic @GoogleAI Thank you so much!!
	Prikaz razgovora ·

	Connor Shorten @CShorten30	29. sij
	This video covers the Evolved Transformer used in the mind-blowing Meena chatbot from @GoogleAI! This video explains the details of how they encode Transformers for automated architecture search! youtu.be/khA-fiC1Wa0 #100DaysOfMLCode
	Prikaži podatke ·