ROI

FOSS Machine Learning News week 41-2020

Welcome to our biweekly selection of Free and Open machine learning news. Created using our own opinionated selection and summary algorithm. FOSS machine learning is crucial for everyone. Machine Learning is a complex technology. So keep it simple.

1 Machine Learning Toolbox

Nice FOSS collections for Machine Learning are always worth sharing. This page contains useful libraries found by the author when working on Machine Learning projects. The libraries are organized below by phases of a typical Machine Learning project.

(Link)

2 IGEL: train/fit, test and use ML models without writing code

Nice ML library. The goal of the project is to provide machine learning for everyone, both technical and non-technical users. I hate buzz terms like nocode or lowcode. So I state: Playing with this library just can save you some valuable time. igel is built on top of scikit-learn. It provides a simple way to use machine learning without writing a single line of code. All you need is a yaml (or json) file, where you need to describe what you are trying to do. That’s it! Igel supports all sklearn’s machine learning functionality, whether regression, classification or clustering. Precisely, you can use 63 different machine learning model in igel.

(Link)

3 MATHWASHING:LIES, DAMN LIES AND ALGORITHMS

Great read.  Mathwashing = When power and bias hide behind the facade of ‘neutral’ math. As maintainer of the FOSS ML blog I only recently noticed this great page of Tijmen Schep.

(Link)

4 Real-Time License Plate Identification System

I always love simple hackable ML applications. To learn or to improve. This collection of python scripts created to be used with Tensorflow is just fun to hack.

(Link)

5 scikit-survival 0.14 with Improved Documentation Released

For a full list of changes in scikit-survival 0.14.0, please see the release notes. Some of these were available as separate Jupyter notebooks previously, such as the guide on Evaluating Survival Models. Moreover, the documentation now contains a User Guide section that bundles several topics surrounding the use of scikit-survival. The biggest change in this release is actually not in the code, but in the documentation. Pre-built conda packages are available for Linux, macOS, and Windows via conda install -c sebp scikit-survival Alternatively, scikit-survival can be installed from source following these instructions.

(Planet GNOME)

6 Machine Learning straight through SQL

Mysql or MariaDB is a rdms that is used at large. Machine learning is one area that cannot succeed without data. Traditionally, machine learning frameworks read it from CSV files or similar data sources. This brings an interesting set of challenges because in most cases the data is stored in databases, not simple raw files. This article is a nice and short tutorial.

(MariaDB)

7 My computational framework for the brain

A generative model for an image of “85” makes a strong prediction that there is an “8” generative model positioned next to a “5” generative model. For example, we can snap together a “purple” generative model and a “jar” generative model to get a “purple jar” generative model. When you imagine a “blank slate” learning algorithm, you should not imagine an empty void that gets filled with data. The “8” generative model, in turn, makes strong predictions that certain contours and textures are present in the visual input stream. I’ll use the term subcortex for the rest of the brain (midbrain, amygdala, etc.). * _ _Aside: Is this the triune brain theory?__ No. Triune brain theory is, from what I gather, a collection of ideas about brain evolution and function, most of which are wrong.

(LessWrong)

8 In the Wild: From ML Models to Pragmatic ML Systems

Enabling robust intelligence in the wild entails learning systems that offer uninterrupted inference while affording sustained learning from varying amounts of data and supervision. The machine learning community has organically broken down this challenging task into manageable sub tasks such as supervised, few-shot, continual, and self-supervised learning; each affording distinct challenges and a unique set of methods. In The Wild (NED). NED naturally integrates the objectives of previous frameworks while removing many of the overly strong assumptions such as predefined training and test phases, sufficient amounts of labeled data for every class, and the closed-world assumption.

(Link)

9 AWS CORD-19 Search: A Neural Search Engine for COVID-19 Literature

Coronavirus disease (COVID-19) has been declared as a pandemic by WHO with thousands of cases being reported each day. Numerous scientific articles are being published on the disease raising the need for a service which can organize, and query them in a reliable fashion. To support this cause we present AWS CORD-19 Search (ACS), a public, COVID-19 specific, neural search engine that is powered by several machine learning systems to support natural language based searches.

(Link)

The FOSS Machine Learning News Blog is a brief overview of open machine learning news from all over the world. Free and Open machine learning means that everyone must be able to develop, test and play and deploy machine learning solutions. Read and share the FOSS ML Guide! And remember:You are invited to join the Free and Open Machine Learning open collaboration project.