Keeping the best articles, blogs, MOOCs I find, & more stuff
-
Learning and the Curse of Dimensionality, a course by Stéphane Mallat at Collège de France (in French only) : http://www.college-de-france.fr/site/en-stephane-mallat/course-2017-2018.htm
-
Comprehensive GitHub repository about Voronoi diagrams : https://github.com/d3/d3-voronoi (https://github.com/MarieCrappe/GreatResources/tree/master/images/voronoi.JPG)
-
Cool interactive demonstration of Voronoi Tesselation : https://bl.ocks.org/mbostock/4060366
-
A Visual Introduction to Machine Learning : http://www.r2d3.us/visual-intro-to-machine-learning-part-1/ One of the best webpages I know to introduce Machine Learning to newbies, a small jewel made with D3JS.
-
Machine Learning Algorithms Cheat Sheet : https://blogs.sas.com/content/subconsciousmusings/2017/04/12/machine-learning-algorithm-use/
-
[French only] Apprentissage, réseaux de neurones et modèles graphiques (Cours du Cnam RCP209) : http://cedric.cnam.fr/vertigo/Cours/ml2
-
Great tool to better understand what is a neural network : http://playground.tensorflow.org/
-
Blog with really cool & precise articles about Deep Learning : https://adeshpande3.github.io/
-
Good article about Transfer Learning in Tensorflow (Feb. 2017) : https://kwotsin.github.io/tech/2017/02/11/transfer-learning.html
-
Unsupervised Feature Learning and Deep Learning, tutorial from Stanford containing a final chapter about Self-Taught Learning : http://ufldl.stanford.edu/tutorial/
-
Wondering how the number of parameters of a neural network can be computed ? Here is a good explanation for that : https://stackoverflow.com/questions/42786717/how-to-calculate-the-number-of-parameters-for-convolutional-neural-network
-
[French only] Reconnaissance des formes et méthodes neuronales (Cours du Cnam RCP208) : http://cedric.cnam.fr/vertigo/Cours/ml
-
An open source toolkit for Computer Vision : https://github.com/tryolabs/luminoth
-
Image Augmentation for Deep Learning with Keras : https://machinelearningmastery.com/image-augmentation-deep-learning-keras/
-
TensorFlow Image Recognition on a Raspberry Pi : https://svds.com/tensorflow-image-recognition-raspberry-pi/
-
Tutorial on Hardware Architectures for Deep Neural Networks : http://eyeriss.mit.edu/tutorial.html
-
Implementing a Neural Network from scratch in Python : http://www.wildml.com/2015/09/implementing-a-neural-network-from-scratch/
-
And for the fun, the project Audio to Obama "Synthesizing Obama: Learning Lip Sync from Audio" : https://grail.cs.washington.edu/projects/AudioToObama/
Generative Adversearial Networks (GANs) are quite interesting as they are unsupervised machine learning algorithms, actually using neural networks. Here are two companies using them for their products :
- http://hackrod.com/
- https://www.autodesk.com/solutions/generative-design
- More interesting stuff about GANs will come ;-)
- Machine Learning to Detect Anomalies from Application Logs : https://www.druva.com/blog/machine-learning-detect-anomalies-application-logs/
- A Machine Learning Approach to Log Analytics : https://logz.io/blog/machine-learning-log-analytics/
- Research Paper "Applying machine learning to software fault-proneness prediction" : https://www.sciencedirect.com/science/article/pii/S0164121207001240
- Evaluating Failure Prediction Models for Predictive Maintenance (Microsoft) : https://blogs.technet.microsoft.com/machinelearning/2016/04/19/evaluating-failure-prediction-models-for-predictive-maintenance/
- An open source project for anomaly detection : https://medium.com/@ment_at/datastream-io-open-source-anomaly-detection-64db282735e0
Good references to learn, practice and stay up-to-date with different programming languages.
Learning to program is often exhilarating and challenging. It can be rewarding and fun... but also, sometimes, exhausting, frustrating, and overwhelming! Here are some websites, courses, documents and articles to make your journey through code smoother and your life easier ;-)
- Great website for code newbies as well as experienced programmers: http://exercism.io/ Exercism provides exercises in the format of mini-quests in over 30 different languages! Among them : Java, PHP, Python, R, Ruby, C, C++ & much more.
[Coming soon]
- PHP-FIG = PHP Standards Recommendations : https://www.php-fig.org/psr/
Master the art of clean code!
[Definition & more to come]
"There's an art and a science to transforming unmaintainable code into elegant simplicity. It takes practice, experimentation, and deep thought." (quote from Exercism.io)
-
The GitHub guide to master Markdown, simple and super useful : https://guides.github.com/features/mastering-markdown/
-
How to resolve conflicts with git : https://help.github.com/articles/resolving-a-merge-conflict-using-the-command-line/
- Learn Enough Command Line to Be Dangerous by Michael Hartl : https://www.learnenough.com/command-line-tutorial A tutorial introduction to the Unix command line
Test-Driven Development (TDD) is a practice that has become mainstream over the past decade or so.
There are many good reasons to do TDD. Here are a few:
- It helps you focus on smaller pieces at a time.
- It protects you against accidentally breaking things later.
- It makes it a little more likely that you'll write simpler code... because complicated code is ridiculously hard to test. There are great conference talks and blog posts about TDD (how to do it, why to do it, how people do it wrong, etc, etc, etc).
Those a GREAT books :
- Software Craftmanship
- Clean Code
- How to send emails with Gmail using Python : http://stackabuse.com/how-to-send-emails-with-gmail-using-python/
- Twitter Follow Bot : https://github.com/rhiever/TwitterFollowBot A Python bot that automates several actions on Twitter, such as following users and favoriting tweets.
- Want to get your hands a bit dirty ? Try to implement this cool data pipeline for Twitter using the Elastic Stack (Elasticsearch, Logstash and Kibana) : https://github.com/TheRinger/ELK_twitter You'll get beautiful, quick and easy-to-use dashboards with those tools !