When looking at WorldBank, WEF and some consulting company reports and white-papers I always wondered if anybody reads them.
Here is a possible answer - No
https://img.washingtonpost.com/blogs/wonkblog/files/2014/05/pdfs.jpg
They do not understand that making content more reachable and SEO-friendly helps long-term. But SEO-friendly websites are usually full of bullshit.
#internet
Here is a possible answer - No
https://img.washingtonpost.com/blogs/wonkblog/files/2014/05/pdfs.jpg
They do not understand that making content more reachable and SEO-friendly helps long-term. But SEO-friendly websites are usually full of bullshit.
#internet
New dimensionality reduction technique - UMAP
- https://github.com/lmcinnes/umap
I will write more as I test it / learn more.
Works well with HDBSCAN and CNNs I guess
- https://goo.gl/9hYAXL
Usage examples
- https://goo.gl/QuYWJF
#data_science
- https://github.com/lmcinnes/umap
I will write more as I test it / learn more.
Works well with HDBSCAN and CNNs I guess
- https://goo.gl/9hYAXL
Usage examples
- https://goo.gl/QuYWJF
#data_science
GitHub
GitHub - lmcinnes/umap: Uniform Manifold Approximation and Projection
Uniform Manifold Approximation and Projection. Contribute to lmcinnes/umap development by creating an account on GitHub.
What is amazing about tf and CUDA / CUDNN drivers - that documentation is not updated when newer versions are released - and they are always changing library file names which is annoying af.
Arguably Google and Nvidia are the richest companies from the whole DS stack - but their documentations is the worst of all the richest companies.
So if you are updating your docker container and libraries suddenly start producing weird errors - look for compatibility guidelines like this one - https://goo.gl/cF3Swy
Of course docs and release note will have no mention of this. Because Google.
Also docker hub contains all the versions of CUDA+CUDDNN packaged, which helps
- https://hub.docker.com/r/nvidia/cuda/
PS
Pytorch has all this embedded into their official repo list
- http://prntscr.com/i6nfsl
Google, why do you make us suffer?
#deep_learning
Arguably Google and Nvidia are the richest companies from the whole DS stack - but their documentations is the worst of all the richest companies.
So if you are updating your docker container and libraries suddenly start producing weird errors - look for compatibility guidelines like this one - https://goo.gl/cF3Swy
Of course docs and release note will have no mention of this. Because Google.
Also docker hub contains all the versions of CUDA+CUDDNN packaged, which helps
- https://hub.docker.com/r/nvidia/cuda/
PS
Pytorch has all this embedded into their official repo list
- http://prntscr.com/i6nfsl
Google, why do you make us suffer?
#deep_learning
pytorials.com
How to install Tensorflow 1.7.0 using official pip package | pytorials.com
Hello everyone. This is going to be a tutorial on how to install tensorflow using official pre-built pip packages. In this tutorial, we will look at how to install tensorflow 1.5.0 CPU and GPU both for Ubuntu as well as Windows OS.
Dockerfile update for CUDA9 - CUDNN7:
- https://goo.gl/JwUXN5
Hello world in PyTorch and tensorflow seem to be working.
#data_science
#deep_learning
- https://goo.gl/JwUXN5
Hello world in PyTorch and tensorflow seem to be working.
#data_science
#deep_learning
Gist
Dockerfile update
Classic / basic CNN papers
Aggregated Residual Transformations for Deep Neural Networks (ResNeXt)
- Authors Xie Saining / Girshick Ross / Dollár Piotr / Tu Zhuowen / He Kaiming
- Link http://arxiv.org/abs/1611.05431
- Resnet and VGG go deeper
- Inception nets go wider. Despite efficiency - they are hard to re-purpose and design
- key idea - add group convolutions to the residual block
- illustrations
-- basic building block https://goo.gl/L8PjUF
-- same block in terms of group convolutions https://goo.gl/fZKmgf
-- overall architecture https://goo.gl/WWSxRv
-- performance - https://goo.gl/vgLN8G - +1% vs resnet
#data_science
#deep_learning
Aggregated Residual Transformations for Deep Neural Networks (ResNeXt)
- Authors Xie Saining / Girshick Ross / Dollár Piotr / Tu Zhuowen / He Kaiming
- Link http://arxiv.org/abs/1611.05431
- Resnet and VGG go deeper
- Inception nets go wider. Despite efficiency - they are hard to re-purpose and design
- key idea - add group convolutions to the residual block
- illustrations
-- basic building block https://goo.gl/L8PjUF
-- same block in terms of group convolutions https://goo.gl/fZKmgf
-- overall architecture https://goo.gl/WWSxRv
-- performance - https://goo.gl/vgLN8G - +1% vs resnet
#data_science
#deep_learning
Some nice boilerplate on neural style transfer
- https://medium.com/artists-and-machine-intelligence/neural-artistic-style-transfer-a-comprehensive-look-f54d8649c199
#deep_learning
- https://medium.com/artists-and-machine-intelligence/neural-artistic-style-transfer-a-comprehensive-look-f54d8649c199
#deep_learning
Medium
Neural Artistic Style Transfer: A Comprehensive Look
Spring Quarter of my freshman year, I took Stanford’s CS 231n course on Convolutional Neural Networks. My final project for the course…
Simple Keras + web service deploy guidelines from FChollet + PyImageSearch
- https://www.pyimagesearch.com/wp-content/uploads/2018/01/keras_api_header.png
- https://blog.keras.io/building-a-simple-keras-deep-learning-rest-api.html?__s=jzpzanwy9jmh18omiik2
- https://www.pyimagesearch.com/2018/01/29/scalable-keras-deep-learning-rest-api/
Also an engineer guy from our team told me that this architecture sucks on high loads because redis will require object serialization, which takes a lot of time for images. Native python process management works better.
#data_science
#deep_learning
- https://www.pyimagesearch.com/wp-content/uploads/2018/01/keras_api_header.png
- https://blog.keras.io/building-a-simple-keras-deep-learning-rest-api.html?__s=jzpzanwy9jmh18omiik2
- https://www.pyimagesearch.com/2018/01/29/scalable-keras-deep-learning-rest-api/
Also an engineer guy from our team told me that this architecture sucks on high loads because redis will require object serialization, which takes a lot of time for images. Native python process management works better.
#data_science
#deep_learning
Some advice on using UMAP algorithm properly from the author
- https://github.com/lmcinnes/umap/issues/37#issuecomment-360807602
#data_science
- https://github.com/lmcinnes/umap/issues/37#issuecomment-360807602
#data_science
GitHub
Multi CPU / GPU capabilities? · Issue #37 · lmcinnes/umap
@lmcinnes As you may have guessed I have several CPUs and GPUs at hand and I work with high-dimensional data. Now I am benching a 500k * 5k => 500k * 2 vector vs. PCA (I need a high level cluste...
Internet digest
- Ben Evans - https://goo.gl/XYKbvr
- RNNs + band names - https://goo.gl/LBBEiP
- Soldiers + fitness trackers = military bases - https://goo.gl/B4yzxX
- Google's new unit - security and ML - https://goo.gl/q1Xnjd
- Apple produces TV content - https://goo.gl/P2X9Gb
- Some bs rumours about Telegram ICO size - https://goo.gl/D4XgPD
- Twitter is plagued by bot-farms - https://goo.gl/ZLHVz1
-- Easy to detect via similar registration dates - https://goo.gl/ZLHVz1
- Podcast about financial innovations in the US - https://goo.gl/kxHUQY
#digest
#internet
- Ben Evans - https://goo.gl/XYKbvr
- RNNs + band names - https://goo.gl/LBBEiP
- Soldiers + fitness trackers = military bases - https://goo.gl/B4yzxX
- Google's new unit - security and ML - https://goo.gl/q1Xnjd
- Apple produces TV content - https://goo.gl/P2X9Gb
- Some bs rumours about Telegram ICO size - https://goo.gl/D4XgPD
- Twitter is plagued by bot-farms - https://goo.gl/ZLHVz1
-- Easy to detect via similar registration dates - https://goo.gl/ZLHVz1
- Podcast about financial innovations in the US - https://goo.gl/kxHUQY
#digest
#internet
Twitter
Jeremy Fiance
recurrent neural network, trained on band names, generates fake @Coachella lineup - reminding us most band names are gibberish
Interesting intutions to understand the mean-shift algorithm
-https://spin.atomicobject.com/2015/05/26/mean-shift-clustering/
- https://goo.gl/QANV5e
Downside - sklearn implementation is slow, you will have to write your own GPU implementation.
#data_science
-https://spin.atomicobject.com/2015/05/26/mean-shift-clustering/
- https://goo.gl/QANV5e
Downside - sklearn implementation is slow, you will have to write your own GPU implementation.
#data_science
Atomic Spin
Mean Shift Clustering
An overview of mean shift clustering (one of my favorite algorithms) and some of its strengths and weaknesses.
Cyclical Learning rates are not merged in Pytorch yet, but they are in the PR stage
- https://github.com/pytorch/pytorch/pull/2016/files
#data_science
#pytorch
- https://github.com/pytorch/pytorch/pull/2016/files
#data_science
#pytorch
GitHub
Adds Cyclical Learning Rates by thomasjpfan · Pull Request #2016 · pytorch/pytorch
Adds feature requested in #1909. Mimics the parameters from https://github.com/bckenstler/CLR. Since Cyclical Learning Rate (CLR) requires updating the learning rate after every batch, I added batc...
2017 DS/ML digest 2
Libraries
- One more RL library (last year saw 1 or 2) http://ray.readthedocs.io/en/latest/rllib.html
- Speech recognition from facebook - https://github.com/facebookresearch/wav2letter
- Even better speech generation than WaveNet - https://goo.gl/mTwyoV - I cannot tell computer apart
Industry (overdue news)
- Nvidia does not like it's consumer GPUs deployed in data centers https://goo.gl/n8mkxk
- Clarifai kills forevery https://goo.gl/PxcjvT
- Google search and gorillas vs. black people - https://goo.gl/t6LwLN
Blog posts
- Baidu - dataset size vs. accuracy https://goo.gl/j6M5ZP (log-scale)
-- https://goo.gl/AYan3f
-- https://goo.gl/JyVNHG
Datasets
- New Youtube actions dataset - https://arxiv.org/abs/1801.03150
-- http://arxiv.org/abs/1801.03150
Papers - current topic - meta learning / CNN optimization and tricks
- Systematic evaluation of CNN advances on the ImageNet https://arxiv.org/abs/1606.02228
-- http://prntscr.com/i8il35
- TRAINING DEEP NEURAL NETWORKS ON NOISY LABELS WITH BOOTSTRAPPING http://arxiv.org/abs/1412.6596
-- http://prntscr.com/i8iq1p
- Cyclical Learning Rates for Training Neural Networks http://arxiv.org/abs/1506.01186
-- http://prntscr.com/i8iqjx
- SEARCHING FOR ACTIVATION FUNCTIONS - http://arxiv.org/abs/1710.05941
-- http://prntscr.com/i8l0sd
-- http://prntscr.com/i8l5dp
- Large batch => train Imagenet in 15 mins
-- http://arxiv.org/abs/1711.04325
- Practical analysis of CNNs
-- http://arxiv.org/abs/1605.07678
#digest
#data_science
#deep_learning
Libraries
- One more RL library (last year saw 1 or 2) http://ray.readthedocs.io/en/latest/rllib.html
- Speech recognition from facebook - https://github.com/facebookresearch/wav2letter
- Even better speech generation than WaveNet - https://goo.gl/mTwyoV - I cannot tell computer apart
Industry (overdue news)
- Nvidia does not like it's consumer GPUs deployed in data centers https://goo.gl/n8mkxk
- Clarifai kills forevery https://goo.gl/PxcjvT
- Google search and gorillas vs. black people - https://goo.gl/t6LwLN
Blog posts
- Baidu - dataset size vs. accuracy https://goo.gl/j6M5ZP (log-scale)
-- https://goo.gl/AYan3f
-- https://goo.gl/JyVNHG
Datasets
- New Youtube actions dataset - https://arxiv.org/abs/1801.03150
-- http://arxiv.org/abs/1801.03150
Papers - current topic - meta learning / CNN optimization and tricks
- Systematic evaluation of CNN advances on the ImageNet https://arxiv.org/abs/1606.02228
-- http://prntscr.com/i8il35
- TRAINING DEEP NEURAL NETWORKS ON NOISY LABELS WITH BOOTSTRAPPING http://arxiv.org/abs/1412.6596
-- http://prntscr.com/i8iq1p
- Cyclical Learning Rates for Training Neural Networks http://arxiv.org/abs/1506.01186
-- http://prntscr.com/i8iqjx
- SEARCHING FOR ACTIVATION FUNCTIONS - http://arxiv.org/abs/1710.05941
-- http://prntscr.com/i8l0sd
-- http://prntscr.com/i8l5dp
- Large batch => train Imagenet in 15 mins
-- http://arxiv.org/abs/1711.04325
- Practical analysis of CNNs
-- http://arxiv.org/abs/1605.07678
#digest
#data_science
#deep_learning