Data Science Breakfast in Paris. Thanks again for coming, hopefully this will setup a regular DS Breakfast in Paris.

​​Generalization in Deep Networks: The Role of Distance from Initialization

Why it's important to take into account the initialization to explain generalization.

ArXiV: https://arxiv.org/abs/1901.01672

#DL #NN

​​Reproducibility tool for #Jupyter Notebooks

Link: https://mybinder.org

#DS #github #reproducibleresearch

​​POET: Endlessly Generating Increasingly Complex and Diverse Learning Environments and their Solutions through the Paired Open-Ended Trailblazer

POET: it generates its own increasingly complex, diverse training environments & solves them. It automatically creates a learning curricula & training data, & potentially innovates endlessly.

Link: https://eng.uber.com/poet-open-ended-deep-learning/

#RL #Uber

​​Super-resolution GANs for improving the texture resolution of old games.

It is what it is. #GAN to enhance textures in old games making them look better.

ArXiV: https://arxiv.org/abs/1809.00219
Link: https://www.gamespot.com/forums/pc-mac-linux-society-1000004/esrgan-is-pretty-damn-amazing-trying-max-payne-wit-33449670/

#gaming #superresolution

Scikit-learn drops support of Python2.7 with new PR.

It means scikit-learn master now requires Python >= 3.5.

https://github.com/scikit-learn/scikit-learn/pull/12639

#scikitlearn

​​DeepTraffic — new RL competition hosted by #MIT

Link: https://selfdrivingcars.mit.edu/deeptraffic/
Github: https://github.com/lexfridman/deeptraffic

#RL #selfdrivingcar

A visual exploration of Gaussian Processes: beautiful interactive plots and a brief tutorial to make GPs more approachable

Link: https://www.jgoertler.com/visual-exploration-gaussian-processes/

#Statistics #GP #GaussianProcesses

Evaluating gambles using dynamics

Link: https://aip.scitation.org/doi/10.1063/1.4940236

#Statistics #Gambling

​​How Uber predicts prices

Engineering Uncertainty Estimation in Neural Networks for Time Series Prediction at Uber

Link: https://eng.uber.com/neural-networks-uncertainty-estimation/

#RNN #LSTM #Uber

Plug-and-play differential privacy for your tensorflow code

#GoogleAI has just released a new library for training machine learning models with (differential) privacy for training data.

where you would write tf.train.GradientDescentOptimizer
instead just swap in the DPGradientDescentOptimizer


Tutorial: https://github.com/tensorflow/privacy/blob/master/tutorials/mnist_dpsgd_tutorial.py
Link: https://github.com/tensorflow/privacy

#Privacy #tensorflow

​​Desnapify

Logical followup of #pix2pix project by Isola et al., based on on Keras implementation by Thibault de Boissiere allows to remove that kat/dog faces from #Snapchat photoes.


Github: https://github.com/ipsingh06/ml-desnapify
Mentioned #Keras repo: https://github.com/tdeboissiere/DeepLearningImplementations/tree/master/pix2pix

#DL

How I used NLP (Spacy) to screen Data Science Resumes

Example on how #notAIyet can be used to ease day-to-day job.

Link: https://towardsdatascience.com/do-the-keywords-in-your-resume-aptly-represent-what-type-of-data-scientist-you-are-59134105ba0d

#NLP #HR #DL

AutoML: Automating the design of machine learning models for autonomous driving

Link: https://medium.com/waymo/automl-automating-the-design-of-machine-learning-models-for-autonomous-driving-141a5583ec2a

#Waymo #automl #DL #selfdriving #Google

Valuing Life as an Asset, as a Statistic and at Gunpoint

Ever wondered, how much your life is worth? This is an article about Life as an asset evaluation. It is extremely useful for insuarance companies and as a metric to calculate compensations in case of tragic events, but it is also a key to understand, how valuable (or not) life is.

Math is beautiful.

Link: https://papers.ssrn.com/sol3/papers.cfm?abstract_id=3156911

#math #life #insurance #statistics

Learning from Dialogue after Deployment: Feed Yourself, Chatbot!

From abstract: The self-feeding chatbot, a dialogue agent with the ability to extract new training examples from the conversations it participates in.

This is an article about chatbot which is capable of true online learning. There is also a venturebeat article on the subject, covering the perspective: «Facebook and Stanford researchers design a chatbot that learns from its mistakes».


Venturebeat: https://venturebeat.com/2019/01/17/facebook-and-stanford-researchers-design-a-chatbot-that-learns-from-its-mistakes/
ArXiV: https://arxiv.org/abs/1901.05415

#NLP #chatbot #facebook #Stanford

🤓Interesting note on weight decay vs L2 regularization

In short, the was difference when moving from caffe (which implements weight decay) to keras (which implements L2). That led to different results on the same net architecture and same set of hyperparameters.

Link: https://bbabenko.github.io/weight-decay/

#DL #nn #hyperopt #hyperparams

​​IQ is largely a pseudoscientific swindle

Note by Nassim Taleb on how IQ works. He shows that high-IQ is not well-correlated with wealth or overall cognitive performance.

Link: https://medium.com/incerto/iq-is-largely-a-pseudoscientific-swindle-f131c101ba39

#statistics #iq #fallacy

Implementing a ResNet model from scratch.

Well-written and explained note on how to build and train a ResNet model from ground zero.

Link: https://towardsdatascience.com/implementing-a-resnet-model-from-scratch-971be7193718

#ResNet #DL #CV #nn #tutorial

Understanding Convolutional Neural Networks through Visualizations in PyTorch

Explanation of how #CNN works

Link: https://towardsdatascience.com/understanding-convolutional-neural-networks-through-visualizations-in-pytorch-b5444de08b91

#PyTorch #nn #DL