After Google released Bilateral NN for image enhancement (https://groups.csail.mit.edu/graphics/hdrnet/) they not stopped and created new cool Night Sight algorithm (https://www.theverge.com/2018/11/14/18092660/google-night-sight-review-pixel-2-3-camera-photos-image-quality)
Hope we will see paper for it soon))
Hope we will see paper for it soon))
Good explanation of basic clustering algorithms
https://towardsdatascience.com/the-5-clustering-algorithms-data-scientists-need-to-know-a36d136ef68
https://towardsdatascience.com/the-5-clustering-algorithms-data-scientists-need-to-know-a36d136ef68
Medium
The 5 Clustering Algorithms Data Scientists Need to Know
Clustering is a Machine Learning technique that involves the grouping of data points. Given a set of data points, we can use a clustering algorithm to classify each data point into a specific group…
New thing that may replace RNN netwokrs
https://arxiv.org/abs/1808.03867
https://arxiv.org/abs/1808.03867
Pavel Pleskov & Pavel Ostiakov got first place on Google Doodles Classification Challenge. You can read about their ideas and tries here: https://www.kaggle.com/c/quickdraw-doodle-recognition/discussion/73738
Not our case, but still very interesting)
https://www.hackerone.com/blog/Test-your-hacking-skills-real-world-simulated-bugs
https://www.hackerone.com/blog/Test-your-hacking-skills-real-world-simulated-bugs
HackerOne
Test your hacking skills on real-world simulated bugs
Five sandbox environments of recently disclosed hacktivity reports available for anyone to test their hacking skills and see if they can replicate the same bug that was discovered. #hackon
CBAM == Spatial + Channel attention module
https://arxiv.org/pdf/1807.06521.pdf
https://arxiv.org/pdf/1807.06521.pdf
Thing that you should definitely read https://arxiv.org/abs/1806.07366
New awesome GAN paper))
https://arxiv.org/abs/1812.04948
https://arxiv.org/abs/1812.04948
Rails Reactor Lecture - Recommendation System. Right now online https://www.facebook.com/RailsReactor/videos/2263385110398870/UzpfSTE2MTYyODUzNTUzNDE4NTQ6Vks6MjAwNzc1NTc3Mjg1MzUwOA/?acontext=%7B%22ref%22%3A%2229%22%2C%22ref_notif_type%22%3A%22admin_plan_mall_activity%22%2C%22action_history%22%3A%22null%22%7D¬if_id=1544807988939694¬if_t=admin_plan_mall_activity
Facebook
Rails Reactor
Ihor Kroosh speaks about Recommender Systems. To watch more videos like this and to be notified when new metups are announced, follow us: https://www.facebook.com/RailsReactor/ and interact with...
The latest improvement in GANs
https://arxiv.org/abs/1812.04948
https://arxiv.org/abs/1812.04948
And here is video of it
https://youtu.be/kSLJriaOumA
https://youtu.be/kSLJriaOumA
YouTube
A Style-Based Generator Architecture for Generative Adversarial Networks
Paper (PDF):
https://stylegan.xyz/paper
Authors:
Tero Karras (NVIDIA)
Samuli Laine (NVIDIA)
Timo Aila (NVIDIA)
Abstract:
We propose an alternative generator architecture for generative adversarial networks, borrowing from style transfer literature. The new…
https://stylegan.xyz/paper
Authors:
Tero Karras (NVIDIA)
Samuli Laine (NVIDIA)
Timo Aila (NVIDIA)
Abstract:
We propose an alternative generator architecture for generative adversarial networks, borrowing from style transfer literature. The new…
New interesting paper in Super Resolution area https://arxiv.org/abs/1812.04240
arXiv.org
Unsupervised Degradation Learning for Single Image Super-Resolution
Deep Convolution Neural Networks (CNN) have achieved significant performance
on single image super-resolution (SR) recently. However, existing CNN-based
methods use artificially synthetic...
on single image super-resolution (SR) recently. However, existing CNN-based
methods use artificially synthetic...
Collection of MIT courses about Machine Learning
https://deeplearning.mit.edu/
https://deeplearning.mit.edu/
Lex Fridman | MIT Lectures
Lectures on Deep Learning, Robotics, and AI | Lex Fridman | MIT
Lectures on AI given by Lex Fridman and others at MIT.
Tough stuff for real learners - Indian Driving Dataset
https://idd.insaan.iiit.ac.in/
https://idd.insaan.iiit.ac.in/
Organic computers may be our future https://phys.org/news/2018-12-amoeba-approximate-solutions-np-hard-problem.html
phys.org
Amoeba finds approximate solutions to NP-hard problem in linear time
Researchers have demonstrated that an amoeba—a single-celled organism consisting mostly of gelatinous protoplasm—has unique computing abilities that may one day offer a competitive alternative to ...
Interesting way of learning AI by yelling at it https://youtu.be/pc_k-sgUYmY
YouTube
DeepMind’s Take on How To Create a Benign AI
The paper "Scalable agent alignment via reward modeling: a research direction" is available here:
1. https://arxiv.org/abs/1811.07871
2. https://medium.com/@deepmindsafetyresearch/scalable-agent-alignment-via-reward-modeling-bf4ab06dfd84
Pick up cool perks…
1. https://arxiv.org/abs/1811.07871
2. https://medium.com/@deepmindsafetyresearch/scalable-agent-alignment-via-reward-modeling-bf4ab06dfd84
Pick up cool perks…
Free dataset for cardio rhythm classification
https://irhythm.github.io/cardiol_test_set/
https://irhythm.github.io/cardiol_test_set/