| Tweetovi |
| archit kaushal proslijedio/la je tweet | ||
|
Richard Feynman
@ProfFeynman
|
4. velj |
|
Life is not a competition, it's a game. It's not about winning or losing, it's about all the fun we can have before it ends!
|
||
|
|
||
| archit kaushal proslijedio/la je tweet | ||
|
Roger Federer
@rogerfederer
|
31. sij |
|
Challenge accepted!
What’s your team name?
Ours is #Gateserer 😎 twitter.com/Trevornoah/sta…
|
||
|
|
||
| archit kaushal proslijedio/la je tweet | ||
|
Richard Feynman
@ProfFeynman
|
30. sij |
|
Feynman Lessons for Learning: 🧠
1) Understanding is more important than memorization!
2) Learn principles, not formulas.
3) Ask questions!
4) Read Books every day.
5) Teaching is a powerful tool to learning. pic.twitter.com/lU8aE8TI6q
|
||
|
|
||
| archit kaushal proslijedio/la je tweet | ||
|
Thang Luong
@lmthang
|
28. sij |
|
Introducing #MeenaBot, a 2.6B-param open-domain chatbot with near-human quality. Remarkably, we show strong correlation between perplexity & humanlikeness!
Paper: arxiv.org/abs/2001.09977
Sample conversations: github.com/google-researc… twitter.com/GoogleAI/statu… pic.twitter.com/3xNSV4r4uB
|
||
|
|
||
| archit kaushal proslijedio/la je tweet | ||
|
Google AI
@GoogleAI
|
28. sij |
|
Check out Meena, a new state-of-the-art open-domain conversational agent, released along with a new evaluation metric, the Sensibleness and Specificity Average, which captures basic, but important attributes for normal conversation. Learn more below! goo.gle/36zB8Wj
|
||
|
|
||
| archit kaushal proslijedio/la je tweet | ||
|
deeplearning.ai
@deeplearningai_
|
28. sij |
|
Test your image classification model with your phone camera! Learn how to deploy models with TensorFlow Lite: bit.ly/2tUGOg9 pic.twitter.com/8bjAY6LmHU
|
||
|
|
||
| archit kaushal proslijedio/la je tweet | ||
|
Durk Kingma
@dpkingma
|
27. sij |
|
Another great result demonstrating that VAEs (deep learning + amortized variational inference) make a lot of sense for data compression. Its loss function directly maximizes compressibility, and the resulting codec is fully parallelizable. twitter.com/TacoCohen/stat…
|
||
|
|
||
| archit kaushal proslijedio/la je tweet | ||
|
Andrew Trask
@iamtrask
|
25. sij |
|
When I learn new idea, I must repeatedly learn it from multiple #tutorials before it *clicks*
If you're learning #convolutional nets - add this to your list
It discusses #CNNs for:
- images
- audio
- databases
#100DaysOfMLCode #100DaysOfCode #AI
brohrer.github.io/how_convolutio… pic.twitter.com/LKURUK36QQ
|
||
|
|
||
| archit kaushal proslijedio/la je tweet | ||
|
L.O.S.T
@LoStSoUl1342
|
18. sij |
|
umeedon se ha ghayal ...umeeed pe zinda ha ✊💦
|
||
|
|
||
| archit kaushal proslijedio/la je tweet | ||
|
L.O.S.T
@LoStSoUl1342
|
22. sij |
|
bnchod yaha cheeeinnk aane par log god bless you bolte ha aur mere muh se behnchod niklta ha
|
||
|
|
||
| archit kaushal proslijedio/la je tweet | ||
|
Boris Becker
@TheBorisBecker
|
15. sij |
|
Amazing guys !!! twitter.com/AustralianOpen…
|
||
|
|
||
| archit kaushal proslijedio/la je tweet | ||
|
The Web Foundation
@webfoundation
|
14. sij |
|
What advancements in #AI can we expect this year?
@VentureBeat asked industry experts from Google, IBM and more for their predictions.
#TheWebThisWeek
venturebeat.com/2020/01/02/top…
|
||
|
|
||
| archit kaushal proslijedio/la je tweet | ||
|
Facebook AI
@facebookai
|
14. sij |
|
By restructuring math expressions as a language, Facebook AI has developed the first neural network that uses symbolic reasoning to solve advanced mathematics problems. ai.facebook.com/blog/using-neu… pic.twitter.com/IL2H8ygDYC
|
||
|
|
||
| archit kaushal proslijedio/la je tweet | ||
|
Richard Feynman
@ProfFeynman
|
14. sij |
|
If you really want to do something, you'll find a way. If you don't, you'll find an excuse. pic.twitter.com/tSBuD1pKQ5
|
||
|
|
||
| archit kaushal proslijedio/la je tweet | ||
|
Rahul Kanwal
@rahulkanwal
|
13. sij |
|
|
||
| archit kaushal proslijedio/la je tweet | ||
|
Richard Feynman
@ProfFeynman
|
11. sij |
|
1. Never stop learning.
2. See failure as a beginning.
3. Teach others what you know.
4. Assume nothing, question everything.
5. Analyze objectively.
6. Practice humility.
7. Respect constructive criticism.
8. Love what you do.
9. Give credit where it's due.
10. Take initiative.
|
||
|
|
||
| archit kaushal proslijedio/la je tweet | ||
|
Rahul Kanwal
@rahulkanwal
|
11. sij |
|
Forget what netas think, fact that so many journalists from other organisations, including Times Now, Republic, Zee News have messaged, tweeted and called to congratulate for @IndiaToday #JNUTapes shows there’s hunger to do good journalism. Unearth truth. Don’t push propaganda.
|
||
|
|
||
| archit kaushal proslijedio/la je tweet | ||
|
arXiv Daily
@arXiv_Daily
|
10. sij |
|
A Robot that Learns Connect Four Using Game Theory and Demonstrations
deepai.org/publication/a-…
by Ali Ayub et al.
#ArtificialIntelligence #ActiveLearning
|
||
|
|
||
| archit kaushal proslijedio/la je tweet | ||
|
Daniel Bourke
@mrdbourke
|
10. sij |
|
2011-2013: Failed university, learned how to learn.
2015-2016: Failed to love myself, learned to love myself.
2016-2017: Failed startup, learned to code.
2018-2019: Failed financial goals, employed myself.
Failure is opportunity in disguise.
|
||
|
|
||
| archit kaushal proslijedio/la je tweet | ||
|
Daniel Bourke
@mrdbourke
|
10. sij |
|
To those learning ML,
You’ll see work from @googleai, FB + others and be amazed.
You also might think, “there’s no way I could do that.” And get discouraged.
How do I know?
Because I think that.
Remind yourself:
- Learning takes time
- You get worse before you get better
|
||
|
|
||