Very interesting point of view from one of the Top RL researchers
https://youtu.be/wEgq6sT1uq8
https://youtu.be/wEgq6sT1uq8
YouTube
A Bitter AI Lesson - Compute Reigns Supreme!
📝 The article "The Bitter Lesson" is available here:
http://www.incompleteideas.net/IncIdeas/BitterLesson.html
Nice twitter thread on this video: https://twitter.com/karoly_zsolnai/status/1114867598724931585
❤️ Pick up cool perks on our Patreon page: h…
http://www.incompleteideas.net/IncIdeas/BitterLesson.html
Nice twitter thread on this video: https://twitter.com/karoly_zsolnai/status/1114867598724931585
❤️ Pick up cool perks on our Patreon page: h…
Machine Learning World pinned «Hey guys, i've made small survey to better understand your needs. It will take just few minutes (10 questions). Thanks a lot :) http://bit.ly/2YAwwwe»
From the pinned survey i found many interesting ideas about improving content of this channel. Also there was many questions about courses and starting point for learners.
So while im rethinking all stuff, here is collection of courses that i passed. https://medium.com/machine-learning-world/learning-path-for-machine-learning-engineer-a7d5dc9de4a4
So while im rethinking all stuff, here is collection of courses that i passed. https://medium.com/machine-learning-world/learning-path-for-machine-learning-engineer-a7d5dc9de4a4
Medium
How To Become A Machine Learning Engineer: Learning Path
We will walk you through all the aspects of machine learning from simple linear regressions to the latest neural networks, and you will…
Disney trying to automate making an animation
https://arxiv.org/pdf/1904.05440.pdf
https://arxiv.org/pdf/1904.05440.pdf
#junior #middle #ds #regression
Explanation on some good technics in DS with code based on House Price Competition https://www.kaggle.com/agehsbarg/top-10-0-10943-stacking-mice-and-brutal-force
Explanation on some good technics in DS with code based on House Price Competition https://www.kaggle.com/agehsbarg/top-10-0-10943-stacking-mice-and-brutal-force
Kaggle
Top 10 (0.10943): stacking, MICE and brutal force
Explore and run machine learning code with Kaggle Notebooks | Using data from multiple data sources
#junior #ds #forecasting #tutorial https://towardsdatascience.com/an-end-to-end-project-on-time-series-analysis-and-forecasting-with-python-4835e6bf050b
Medium
An End-to-End Project on Time Series Analysis and Forecasting with Python
Time series analysis comprises methods for analyzing time series data in order to extract meaningful statistics and other characteristics…
When you use ImageNet Dataset, but something went wrong)))
Graph Embedding with PyTorch from Facebook
https://github.com/facebookresearch/PyTorch-BigGraph
https://github.com/facebookresearch/PyTorch-BigGraph
GitHub
GitHub - facebookresearch/PyTorch-BigGraph: Generate embeddings from large-scale graph-structured data.
Generate embeddings from large-scale graph-structured data. - facebookresearch/PyTorch-BigGraph
Open Math Coourses from Kyiv Polytechnic Institute (Ukrainian language only)
http://bit.ly/2IX9SZp
http://bit.ly/2IX9SZp
New awesome article from Distill Pub https://distill.pub/2019/activation-atlas/
Distill
Activation Atlas
By using feature inversion to visualize millions of activations from an image classification network, we create an explorable activation atlas of features the network has learned and what concepts it typically represents.
Generating music by OpenAI team https://openai.com/blog/musenet/
Openai
MuseNet
We’ve created MuseNet, a deep neural network that can generate 4-minute musical compositions with 10 different instruments, and can combine styles from country to Mozart to the Beatles. MuseNet was not explicitly programmed with our understanding of music…
Interesting article to read about handling unlabeled data
https://arxiv.org/abs/1905.00546
https://arxiv.org/abs/1905.00546
arXiv.org
Billion-scale semi-supervised learning for image classification
This paper presents a study of semi-supervised learning with large convolutional networks. We propose a pipeline, based on a teacher/student paradigm, that leverages a large collection of...
Google released updated landmark dataset
https://ai.googleblog.com/2019/05/announcing-google-landmarks-v2-improved.html
https://ai.googleblog.com/2019/05/announcing-google-landmarks-v2-improved.html
research.google
Announcing Google-Landmarks-v2: An Improved Dataset for Landmark Recognition & R
Posted by Bingyi Cao and Tobias Weyand, Software Engineers, Google AI Last year we released Google-Landmarks, the largest world-wide landmark rec...
Very interesting paper about optimization of models, with step by step pruning process.
ICLR'19 best paper
https://arxiv.org/abs/1905.01067
ICLR'19 best paper
https://arxiv.org/abs/1905.01067
arXiv.org
Deconstructing Lottery Tickets: Zeros, Signs, and the Supermask
The recent "Lottery Ticket Hypothesis" paper by Frankle & Carbin showed that a simple approach to creating sparse networks (keeping the large weights) results in models that are trainable from...