In Machine Learning where the competition becomes fearsome, I think the ability of choosing the right research question (despite all the noises) is utmost important. Selecting a potential topic which is under-explored (such as low-shot learning) will hopefully open a career path.
1
9
This is exciting. Finally, the community has realized the potential of zero-shot learning.
Want to turn any vision backbone into an image-text model? Want to show the age-old "your model wouldn't recognize a cow on the beach" is a red herring?
That's LiT🔥 (Locked-image Tuning), a new alternative to fine-tuning that combines the best of fine-tuning and zero-shot
1/n🧶
1
1
8
I am delighted that our paper "Dense Feature Composition for Zero-Shot Learning" is accepted to #NeurIPS20. Thank reviewers for giving us a fair evaluation.
I am happy that I could celebrate this with friends. #TheUpAndDownOfLife
4
The most useful operation in Machine Learning. I would say 80% of my codes are Einstein summations.
2
2
Exactly what I am looking for
Sharing my lecture slides on "Recent Developments of Graph Network Architectures" from my deep learning course. It is a review of some exciting works on GNNs published in 2019-2020. #feelthelearn
rb.gy/quo3n6
2
This could be my Christmas-watching list :)
Favorite #NeurIPS2020 presentations and posters this year
PS: heavily biased by what I happened to catch and whom I happened to talk to
PPS: still catching up on talks so the list is rather incomplete and I'd hope to grow
PPPS: with contributions from @ml_collective members
2
Congrats. What a great news.
How lucky I am to take your Advanced Machine Learning course in NEU.
1
2
Amazing tools for visualizing neural network architectures.
I wish I know about these sooner
Are you trying to visualize your deep network just 2 days before the #CVPR2021 deadline? Here are some pretty alternatives to boring tensorboard graphs. (1/n)
1
technologyreview.com/s/53191…
I hope this article could serve as an interesting opinion for everyone trying to uncover the formulation of creativity. Any comments are welcomed especially the counter-arguments.
1
Hang in there.
Some researchers are indeed genius.
But many researchers have to struggle a lot to reach that point (and to maintain their positions).
Life, in general, is hard. Just focusing on improving ourselves is the best strategy to stay positive.
1
1