FOSS Machine Learning News week 19-2020

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 Explainable Deep Learning: A Field Guide for the Uninitiated

Great learning guide for new and starting researchers in the Deep neural network (DNN) field. Deep neural network (DNN) is an indispensable machine learning tool for achieving human-level performance on many learning tasks. Yet, due to its black-box nature, it is inherently difficult to understand which aspects of the input data drive the decisions of the network. This guide is now also included in the updated ML Learning resources section of the FOSS-ML guide.


2 Everything about Pooling layers and different types of Pooling

We have explored the idea and computation details regarding pooling layers in Machine Learning models and different types of pooling operations. Any layer maybe defined by its hyperparameters. here are three parameters the describe a pooling layer

(ML news Blog)

3 Common Sense Comes Closer to Computers

That’s because common sense consists of implicit information — the broad (and broadly shared) set of unwritten assumptions and rules of thumb that humans automatically use to make sense of the world. They surmised that if all the unwritten rules of human common sense could be written down, computers should be able to use them to reason with in the same way that they do arithmetic. Some researchers argue that in order to build real common sense into computers, we will need to make use of phenomena outside language itself, like visual perceptions or embodied sensations. Not all of the responses made sense, but the first two did: He “wanted to start a fire” or “to make a fire.” Two Paths to Common Sense Common sense has been called the “dark matter of AI” — both essential and frustratingly elusive. Common sense lets us read between the lines; we don’t need to be explicitly told that food is typically eaten in restaurants after people order and before they leave a tip.

(Quanta Magazine)

4 and applying deep learning to robotics

Navigate back to Perspectives Navigate back to Insights The Rebirth of Robotics: How Covariant Unlocks the Power of Deep Learning for Robots by Mike Volpi In this post:, Damir Becirovic Most robots these days make use of some form of Deep Learning. But as deep learning continues to “graduate” from academic to commercial use, robots have found a second (or perhaps third) spring. Deep learning and neural networks have been around since the 90s.


5 Do you see what AI sees?

Artificial intelligence can be fooled by certain images—and new research shows that humans tend to agree with the computers.


6 ML impossible: Train 1 billion samples in 5 minutes on your laptop

Creating even a simple machine learning service is a non-trivial task. Even if we ignore the data gathering and augmentation steps, one still needs to understand the data, clean it appropriately, create meaningful features, and then train and tune a model.


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.