Tweets
- Tweets, current page.
- Tweets & replies
You blocked @xpearhead
Are you sure you want to view these Tweets? Viewing Tweets won't unblock @xpearhead
-
Pinned Tweet
Enabling people to converse with chatbots about anything has been a passion of a lifetime for me, and I'm sure of others as well. So I'm very thankful to be able to finally share our results with you all. Hopefully, this will help inform efforts in the area. (1/4)https://twitter.com/lmthang/status/1222234237262159872 …
Show this threadThanks. Twitter will use this to make your timeline better. UndoUndo -
Daniel Adiwardana Retweeted
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!" https://youtu.be/STrrlLG15OY#100DaysOfMLCodeThanks. Twitter will use this to make your timeline better. UndoUndo -
Daniel Adiwardana Retweeted
Had the chance to sit next to Daniel
@xpearhead in the early days of the project and tried out the interactive Meena. It has always been *this* surprising and funny :) BIG Congrats to the team with this publication. The possibilities to build up from here is endless.https://twitter.com/kcimc/status/1222378902821068800 …
Thanks. Twitter will use this to make your timeline better. UndoUndo -
Daniel Adiwardana Retweeted
Meena: new SOTA chatbot from us. One big step towards human-like conversation AI. Look forward to many applications related to that, e.g. 7/24 AI based foreign language tutoring. https://twitter.com/GoogleAI/status/1222230622355087360 …pic.twitter.com/AsvZPtv8dZ
Thanks. Twitter will use this to make your timeline better. UndoUndo -
Daniel Adiwardana Retweeted
New paper: Towards a Human-like Open-Domain Chatbot. Key takeaways: 1. "Perplexity is all a chatbot needs" ;) 2. We're getting closer to a high-quality chatbot that can chat about anything Paper: https://arxiv.org/abs/2001.09977 Blog: https://ai.googleblog.com/2020/01/towards-conversational-agent-that-can.html …pic.twitter.com/5SOBa58qx3
Show this threadThanks. Twitter will use this to make your timeline better. UndoUndo -
Daniel Adiwardana Retweeted
Open-domain conversation is an extremely difficult task for ML systems. Meena is a research effort at
@GoogleAI in this area. It's challenging, but we are making progress towards more fluent and sensible conversations. Nice work, Daniel,@lmthang & everyone involved! https://twitter.com/GoogleAI/status/1222230622355087360 …pic.twitter.com/vjkXoSUHf3
Thanks. Twitter will use this to make your timeline better. UndoUndo -
Bonus: Meena often seems to put together ideas in ways that we don't manage to find matches of in the data. For example saying that "Horses go to Hayvard" in conversation we show in the blog post https://ai.googleblog.com/2020/01/towards-conversational-agent-that-can.html ….
Show this threadThanks. Twitter will use this to make your timeline better. UndoUndo -
"It was trained on movie subtitles?!" I told myself and others in awe. Maybe the potential for generalization was really there. I was truly blessed to be able to later work with
@quocleix and many others on giving continuity to this idea, and turning it into#MeenaResearch. (4/4)Show this threadThanks. Twitter will use this to make your timeline better. UndoUndo -
One day, I came across the paper A Neural Conversational Model (https://arxiv.org/abs/1506.05869 ) by
@OriolVinyalsML and@quocleix. The paper showed sample conversations with an end-to-end learned neural network. (3/4)Show this threadThanks. Twitter will use this to make your timeline better. UndoUndo -
When I was about 9 years old my father taught me how to program, and, to my delight, we built a chatbot. Initially, I couldn't stop working on it, but I no matter how many rules I wrote and how much knowledge I tried to add to its database, it still wasn't what I expected. (2/4)
Show this threadThanks. Twitter will use this to make your timeline better. UndoUndo -
Daniel Adiwardana Retweeted
(1/4) Learning ML engineering is a long slog even for legendary hackers like
@gdb. IMO, the two hardest parts of ML eng are: 1) Feedback loops are measured in minutes or days in ML (compared to seconds in normal eng) 2) Errors are often silent in MLhttps://twitter.com/gdb/status/1156214917365551104 …
Show this threadThanks. Twitter will use this to make your timeline better. UndoUndo -
Daniel Adiwardana Retweeted
XLNet: a new pretraining method for NLP that significantly improves upon BERT on 20 tasks (e.g., SQuAD, GLUE, RACE) arxiv: https://arxiv.org/abs/1906.08237 github (code + pretrained models): https://github.com/zihangdai/xlnet with Zhilin Yang,
@ZihangDai, Yiming Yang, Jaime Carbonell,@rsalakhupic.twitter.com/JboOekUVPQ
Thanks. Twitter will use this to make your timeline better. UndoUndo -
Daniel Adiwardana Retweeted
An interesting trend from this year's CVPR are the numerous new papers on self-supervised learning. Andrew Zisserman gave a nice tutorial: https://project.inria.fr/paiss/files/2018/07/zisserman-self-supervised.pdf … although, there is a lot more geometry-related work as well (e.g. self-supervised depth & friends).
Thanks. Twitter will use this to make your timeline better. UndoUndo -
Daniel Adiwardana Retweeted
Honored to talk w
@AndrewYNg. His@deeplearningai_ courses were my intro to the field & I wouldn't be here w/o his clear & inspiring teaching! I think of these, the@fastdotai courses, and the@OpenAI scholars/fellows, as the 3 essential steps I've taken in this wild journeyhttps://twitter.com/deeplearningai_/status/1131183884081610753 …
1:50Thanks. Twitter will use this to make your timeline better. UndoUndo -
Daniel Adiwardana Retweeted
Translatotron is our experimental model for direct end-to-end speech-to-speech translation, which demonstrates the potential for improved translation efficiency, fewer errors, and better handling of proper nouns. Learn all about it below!https://goo.gle/2Hlf5sQ
Thanks. Twitter will use this to make your timeline better. UndoUndo -
Daniel Adiwardana Retweeted
Really cool application of a differentiable approximation to nearest neighbours (as in e.g. NCA): aligning videos without any supervision.https://twitter.com/debidatta/status/1118659621290307584 …
Thanks. Twitter will use this to make your timeline better. UndoUndo -
Daniel Adiwardana Retweeted
New blog post: "A Recipe for Training Neural Networks" https://karpathy.github.io/2019/04/25/recipe/ … a collection of attempted advice for training neural nets with a focus on how to structure that process over time
Thanks. Twitter will use this to make your timeline better. UndoUndo -
Daniel Adiwardana Retweeted
The reason most (not all) methods don't add value (over baseline) when scaled is because they're "extra training data in disguise", so their benefit vanishes in the high data regimehttps://twitter.com/ilyasut/status/1106323934209662976 …
Thanks. Twitter will use this to make your timeline better. UndoUndo -
Daniel Adiwardana Retweeted
Very first tweet by
@geoffreyhinton after getting Turing Award "Thanks to my graduate students and postdocs whose work won a Turing award. Thanks to my visionary mentors Inman Harvey, David Rumelhart and Terry Sejnowski... " What a humble person! Very few of us would do the same.https://twitter.com/geoffreyhinton/status/1110914561811587072 …Thanks. Twitter will use this to make your timeline better. UndoUndo -
Daniel Adiwardana Retweeted
The toronto brain team celebrated Geoff's Turing award yesterday. We got two cakes, one said Hinton, the other said Turing, that way we could decide which was better.pic.twitter.com/HVe2OStKf9
Thanks. Twitter will use this to make your timeline better. UndoUndo
Loading seems to be taking a while.
Twitter may be over capacity or experiencing a momentary hiccup. Try again or visit Twitter Status for more information.