Interesting picture summarizing several types of techniques used in machine learning, contrasting unsupervised learning with unsupervised learning and reinforcement learning.

The difference between supervised and unsupervised learning is described…

Course material for Richard Weber's course on Probability for first year mathematicians at Cambridge. You can also check Richard's blog (a former colleague of my dad) here. It also includes exams question. This is the base material that needs to be mastered before being accepted in the prestigious Tripo III curriculum at Cambridge. The book (PDF) can be downloaded…

I can't find anymore where this chart, featuring relations between distributions, was first published. I remember seeing it on the Cloudera blog.

Another shorter one featuring the most useful one for statistical analysis, can be found…

In one great video.

Enjoy the video!

Here are two great resources for machine learning and AI practitioners. Other recent free books can be found here. 

1. Free and Open Machine Learning Documentation

This book is all about applying machine learning solutions for real practical use cases. This means the core focus is on outlining how to use machine learning…

News from Google.

Interesting application leveraging very big data, as you can zoom in to check out pretty detailed landscape on a few nearby planets and satellites. It would be even better if it allowed you to simulate space travel. At a speed 32 million times faster than the speed of light, it would take you 4 seconds to reach the closest star (Alpha Centauri):…

The picture below is from the article Machine Learning and Deep Learning frameworks and libraries for large-scale data mining: a survey, posted here.

Authors: Giang Nguyen, Stefan Dlugolinsky, Martin Bobák, Viet…

The picture below was found in some tweets posted by top data science influencers, though its origin is somewhat obscure. 

Many of these methods are described in Wikipedia. Many are also described on Data Science Central, see for instance…

Gradient Descent has a problem of getting stuck in Local Minima. The following alternatives are available. The following is a summary of answers suggested on CrossValided, originally posted here. …

Pandas is an open source, BSD-licensed library providing high-performance, easy-to-use data structures and data analysis tools for the Python programming language.

Hexagonal binning with Hexbin: extract from the Visualization chapter

This reference is available…

The IEEE International Conference on Computer Vision received 4,303 papers and accepted 1,075 for the 2019 summit. Bellow is the best paper award.

Source: see paper listed below…

The title of the eBook is Dive in Deep Learning. Below I list the content of chapter 16, dealing with the math of deep learning. But the whole book (entirely free) is worth reading. This is an interactive deep learning book with code, math, and discussions. It is based on the NumPy interface.

Authors

• Aston Zhang, Amazon Senior Scientist, UIUC Ph.D.
• Zack C. Lipton, Amazon Scientist, CMU Assistant Professor, UCSD Ph.D.
• Mu Li,…

Jupyter notebooks that walk you through the fundamentals of Machine Learning and Deep Learning in Python using Scikit-Learn, Keras and TensorFlow 2. 

Source: from the Support Vector Machines chapter,…

Another free book to learn Machine Learning. It also comes with a Youtube video series available here. 

Content

• Machine Learning Setup
• k-Nearest Neighbors / Curse of…

This list of lists contains books, notebooks, presentations, cheat sheets, and tutorials covering all aspects of data science, machine learning, deep learning, statistics, math, and more, with most documents featuring Python or R code and numerous illustrations or case studies. All this material is available for free, and consists of content mostly created in 2019 and 2018, by various top experts in their respective fields. A few of these documents are available on LinkedIn: see last section…

Interesting GIF visualization. We do not endorse any political opinion, and the picture below is provided only for its visual value, not for its political content.

It was originally posted here. Other visualizations can…

By Soroush Nasiriany, Garrett Thomas, William Wang, Alex Yang. Department of Electrical Engineering and Computer Sciences, University of California, Berkeley. Dated June 24, 2019. This is not the same book as The Math of Machine Learning, also published by the same department at Berkeley, in 2018, and also authored by Garret…

According to Wikipedia, an ANN is based on a collection of connected units or nodes called artificial neurons, which loosely model the neurons in a biological brain. Each connection, like the synapses in a biological brain, can transmit a signal to other neurons. An artificial neuron that receives a signal then processes it and can signal neurons connected to it.

In ANN implementations, the "signal" at a connection is a real number, and the output of each neuron is computed by some…

Technical paper, published in IEEE Xplore.

Abstract: