OpenAI will use PyTorch as a standard now
https://openai.com/blog/openai-pytorch/
https://openai.com/blog/openai-pytorch/
Openai
OpenAI standardizes on PyTorch
We are standardizing OpenAI’s deep learning framework on PyTorch.
👍1
TF published mutation operator for matrix compression with different methods like pruning, quantization, etc in real-time to minimize training process
https://blog.tensorflow.org/2020/02/matrix-compression-operator-tensorflow.html?m=1
https://blog.tensorflow.org/2020/02/matrix-compression-operator-tensorflow.html?m=1
blog.tensorflow.org
Matrix Compression Operator
The TensorFlow blog contains regular news from the TensorFlow team and the community, with articles on Python, TensorFlow.js, TF Lite, TFX, and more.
Interesting conference on March 14 in Kyiv — 8th Data Science UA Conference.
The most complicated algorithms, revolutionary inventions, and technologies all consist of hundreds of the simplest components that use create synergy together.
The ability to understand and create such projects depends on decomposition and simplification.
Register by the link >>> https://bit.ly/2Np7VGy
10% promotional code for our subscribers: ML_World
The most complicated algorithms, revolutionary inventions, and technologies all consist of hundreds of the simplest components that use create synergy together.
The ability to understand and create such projects depends on decomposition and simplification.
Register by the link >>> https://bit.ly/2Np7VGy
10% promotional code for our subscribers: ML_World
Video frames interpolation
https://sites.google.com/view/wenbobao/dain
https://sites.google.com/view/wenbobao/dain
Google
Wenbo Bao's Homepage - DAIN
Abstract
Video frame interpolation aims to synthesize non-existent frames in-between the original frames. While significant advances have been made from the deep convolutional neural networks, the quality of interpolation is often reduced due to large object…
Video frame interpolation aims to synthesize non-existent frames in-between the original frames. While significant advances have been made from the deep convolutional neural networks, the quality of interpolation is often reduced due to large object…
Step by step explained GPT-2 model
https://amaarora.github.io/2020/02/18/annotatedGPT2.html
https://amaarora.github.io/2020/02/18/annotatedGPT2.html
Committed towards better future
The Annotated GPT-2
Introduction Prerequisites Language Models are Unsupervised Multitask Learners Abstract Model Architecture (GPT-2) Model Specifications (GPT) Imports Transformer Decoder inside GPT-2 CONV1D Layer Explained FEEDFORWARD Layer Explained ATTENTION Layer Explained…
Machine Learning World pinned «Interesting conference on March 14 in Kyiv — 8th Data Science UA Conference. The most complicated algorithms, revolutionary inventions, and technologies all consist of hundreds of the simplest components that use create synergy together. The ability to…»
Now even your baby can learn about ML & NN 😂
https://www.amazon.com/Neural-Networks-Babies-Baby-University/dp/1492671207
https://www.amazon.com/Neural-Networks-Babies-Baby-University/dp/1492671207
February 25
Data Science Meetup
Meet speakers:
- Borys Pratsyuk, CTO, Scalarr
Topic: How Big Data and Data Science help fight with fraud
- Alexander Savsunenko, Senior Research Engineer
Subject: Levelling up your data flow
- Michael Korkin, CTO at Everguard
Subject: Thinking outside the bounding box: how to improve safety in dangerous industrial workspaces with computer vision and sensor fusion
Register for meetup: https://data-science.com.ua/events/data-science-meetup
10% discount: MLWorld
Data Science Meetup
Meet speakers:
- Borys Pratsyuk, CTO, Scalarr
Topic: How Big Data and Data Science help fight with fraud
- Alexander Savsunenko, Senior Research Engineer
Subject: Levelling up your data flow
- Michael Korkin, CTO at Everguard
Subject: Thinking outside the bounding box: how to improve safety in dangerous industrial workspaces with computer vision and sensor fusion
Register for meetup: https://data-science.com.ua/events/data-science-meetup
10% discount: MLWorld
Data Science UA
Data Science Meetup #2 - Data Science UA
Interesting paper bout reproducibility in AI/ML from Dr. Edward Raff is a Chief Scientist at Booz Allen Hamilton. He analyzed 255 papers, and successfully reproduce 162 from them.
A 62% success rate is higher than many meta-analyses from other sciences, and I suspect my 62% number is lower than reality
Interesting facts:
1. Having fewer equations per page makes a paper more reproducible.
2. Empirical papers may be more reproducible than theory-oriented papers.
3. Sharing code is not a panacea
4. Having detailed pseudo code is just as reproducible as having no pseudo code.
5. Creating simplified example problems do not appear to help with reproducibility.
6: Please, check your email (papers of people who answer on emails is more reproducible)
https://thegradient.pub/independently-reproducible-machine-learning/
A 62% success rate is higher than many meta-analyses from other sciences, and I suspect my 62% number is lower than reality
Interesting facts:
1. Having fewer equations per page makes a paper more reproducible.
2. Empirical papers may be more reproducible than theory-oriented papers.
3. Sharing code is not a panacea
4. Having detailed pseudo code is just as reproducible as having no pseudo code.
5. Creating simplified example problems do not appear to help with reproducibility.
6: Please, check your email (papers of people who answer on emails is more reproducible)
https://thegradient.pub/independently-reproducible-machine-learning/
The Gradient
Quantifying Independently Reproducible Machine Learning
Many warn that Artificial Intelligence has a serious reproducibility crisis, but is it so? Some conclusions from the author's experience trying to replicate 255 papers.
March 3, Kyiv
Data Science Meetup
Meet speakers:
- Nazar Shmatko, VP of engineering, RefaceAI
Topic: The success of generative models and how to reach it
- Philip Shurpik, Head of ML production, RefaceAI
Topic: ML & Video Pipelines - path to scalable production
Register for meetup: https://data-science.com.ua/en/events/data-science-meetup-2
Promocode: ML_World
Data Science Meetup
Meet speakers:
- Nazar Shmatko, VP of engineering, RefaceAI
Topic: The success of generative models and how to reach it
- Philip Shurpik, Head of ML production, RefaceAI
Topic: ML & Video Pipelines - path to scalable production
Register for meetup: https://data-science.com.ua/en/events/data-science-meetup-2
Promocode: ML_World
Data Science UA
Data Science Meetup #2 - Data Science UA