AI, Python, Cognitive Neuroscience

Rigorously testing Machine learning models using meta-learning. We show how a Neural Process-based meta-learning formulation allows us to efficiently search for hard examples.
inDeepMind, Interested in adversarial tests and reinforcement learning? We combine meta-learning in a general probabilistic paradigm to detect failures, helping us build robust algorithms. Includes results on recommender systems and control: http://arxiv.org/abs/1903.11907

✴️ @AI_Python_EN

Learning the Depths of Moving People by Watching Frozen People” (http://goo.gle/2x4tEuQ ), recipient of a #CVPR2019 Best Paper Honorable Mention Award. Learn more about the paper at
http://goo.gle/2ZuZtJt

✴️ @AI_Python_EN

Best Papers Awards #ICML2019
The Thirty-sixth International Conference on Machine Learning, Long Beach, USA

(1)Challenging Common Assumptions in the Unsupervised Learning of Disentangled Representations https://arxiv.org/pdf/1811.12359.pdf
Congratulations to the GoogleAI team of Francesco Locatello, Stefan Bauer, Mario Lucic, Gunnar Rätsch, Sylvain Gelly,Bernhard Schölkopf, Olivier Bachem

(2)Rates of Convergence for Sparse Variational Gaussian Process Regression
https://arxiv.org/pdf/1903.03571.pdf
Kudos to David R. Burt, Carl E. Rasmussen, Mark van der Wilk of University of Cambridge

✴️ @AI_Python_EN

AlphaStar: Mastering the Game of StarCraft II

Talk by David Silver: https://slideslive.com/38916905/alphastar-mastering-the-game-of-starcraft-ii

#ArtificialIntelligence #DeepLearning #ReinforcementLearning

✴️ @AI_Python_EN

A video is now online of our ICML Tutorial on Recent Advances in Population-Based Search for Deep Neural Networks: Quality Diversity, Indirect Encodings, and Open-Ended Algorithms. We hope you find it valuable!

https://www.youtube.com/watch?v=g6HiuEnbwJE&feature=youtu.be
✴️ @AI_Python_EN

Oldies but Goldies: D. Lee et S. Seung, Learning the parts of objects by non-negative matrix factorization, Nature (1999). Lee and Seung proposed the most popular matrix factorization algorithm, which operates by multiplicative updates.
https://en.wikipedia.org/wiki/Non-negative_matrix_factorization

✴️ @AI_Python_EN

#ACL2019 paper "Self-attentional Models for Lattice Inputs" proposes a method to apply Transformers to graphs encoding ambiguity from an upstream system such as speech recognition. Nice results, and much faster on speech translation benchmarks!
https://arxiv.org/abs/1906.01617

✴️ @AI_Python_EN

A major benefit of self-supervision is we can truly scale and adapt on the fly. It could be 10% behind supervised ImageNet, it would still do better in real life. We show in http://online-objects.github.io that the longer our model looks at objects, the better it understands them.

✴️ @AI_Python_EN

[about] https://medium.com/@jasonphang/deep-neural-networks-improve-radiologists-performance-in-breast-cancer-screening-565eb2bd3c9f

[code] https://github.com/nyukat/breast_cancer_classifier

[preprint] https://arxiv.org/pdf/1903.08297.pdf

[data specs] https://cs.nyu.edu/~kgeras/reports/datav1.0.pdf

[ICML '19] https://aiforsocialgood.github.io/icml2019/acceptedpapers.htm

#AI #radiology #breastcancer

✴️ @AI_Python_EN

Great to see lots of interest in meta-learning at #CVPR2019 ! Had trouble getting in the room to give my talk. My talk was based on our icmlconf tutorial with Slides, video, references
here: http://sites.google.com/view/icml19metalearning

✴️ @AI_Python_EN

Group For Who Have a Passion For:

1. Artificial Intelligence
2. Machine Learning
3. Deep Learning
4. Data Science
5. Computer vision
6. Image Processing

https://t.me/DeepLearningML

✴️ @AI_Python_EN

Despite their popularity in media and among amateurs, GANs have quite limited practical application. But this specific result has a huge cultural value.

A neural network was used to recreate the Doom Guy in high-res: https://lnkd.in/eERQ7MJ

✴️ @AI_Python_EN

Berkeley/FAIR AI revolution slogans:
- Jitendra Malik: "Supervision is the opium of the AI researcher"
- Alyosha Efros: "The AI revolution will not be supervised"
- Yann LeCun: "self-supervised learning is the cake,

https://www.facebook.com/722677142/posts/10156036317282143/

✴️ @AI_Python_EN

Learn about Learning from Unlabeled Videos at #CVPR2019

https://sites.google.com/view/luv2019/home?authuser=0

✴️ @AI_Python_EN

Facebook Open-sources AI Habitat, an advanced simulation platform for embodied AI research
Details:
https://lnkd.in/eT-xvqh
#ArtificialIntelligence #MachineLearning #DataScience

✴️ @AI_Python_EN

The state-of-the-art in expert recommendation systems

https://www.sciencedirect.com/science/article/abs/pii/S0952197619300703

✴️ @AI_Python_EN

Deep Learning: AlphaGo Zero Explained In One Picture

By L.V.: https://lnkd.in/eJMAKfy

#ArtificialIntelligence #DeepLearning #NeuralNetworks #ReinforcementLearning

✴️ @AI_Python_EN

For those of you who have been waiting for the Neural Network Visualization course to be completed before you purchase, you are in luck!
https://lnkd.in/eNeue6N

For those who invested early, your foresight is rewarded. At your leisure, you can now smugly visit the course curriculum page and walk through the entire course.

The course has been a pleasure to put together and I hope you get as much out of it as I have. I look forward to reading your comments on the lessons.

✴️ @AI_Python_EN

Conceptualizing systemically and in terms of conditional probabilities, rather than categorically, are perhaps the two keys to statistical thinking.

"What the heck does that mean?" you might wonder. A concrete example is medicine. Doctors are usually not biostatisticians but are trained to think statistically.

This is why they say things like: "If there are no serious complications and no side effects from the medication, and no deterioration in liver function, then the prognosis is good."

One way to define statistical thinking is a series of questions we can ask ourselves, such as:

Am I asking the right questions?

Are there rival explanations I haven't considered?

Am I confusing the possible with the plausible or the plausible with fact?

Are there unobserved variables or other confounders I haven’t accounted for?

Am I confusing cause with effect, or correlation with causation?

Am I drawing conclusions about fruit based only on apples?

Given A and B, if I do C and D, what are the likely outcomes?

✴️ @AI_Python_EN

Challenging Common Assumptions in the Unsupervised Learning of Disentangled Representations"
http://goo.gle/2IyFqTO
recipient of an #ICML2019 Best Paper Award! Learn more in the blog post at
http://goo.gle/2KaMs48 .

✴️ @AI_Python_EN