Understanding the learning dynamics of neural networks is one of the key issues for the improvement of optimization algorithms as well as for the theoretical comprehension of why deep neural nets work so well today. In this paper, we introduce a random matrix-based framework to analyze the learning dynamics of a single-layer linear network on a binary classification problem, for data of simultaneously large dimension and size, trained by gradient descent. Our results provide rich insights into common questions in neural nets, such as overfitting, early stopping and the initialization of training, thereby opening the door for future studies of more elaborate structures and models appearing in today’s neural networks. The Dynamics of Learning: A Random Matrix Approach

By John Sullivan,DataOptimal

Despite the advances made in artificial intelligence, software agents, and robotics, there is little we see today that we can truly call a fully autonomous system. We conjecture that the main inhibitor for advancing autonomy is lack of trust. Trusted autonomy is the scientific and engineering field to establish the foundations and ground work for developing trusted autonomous systems (robotics and software agents) that can be used in our daily life, and can be integrated with humans seamlessly, naturally and efficiently. In this paper, we review this literature to reveal opportunities for researchers and practitioners to work on topics that can create a leap forward in advancing the field of trusted autonomy. We focus the paper on the `trust’ component as the uniting technology between humans and machines. Our inquiry into this topic revolves around three sub-topics: (1) reviewing and positioning the trust modelling literature for the purpose of trusted autonomy; (2) reviewing a critical subset of sensor technologies that allow a machine to sense human states; and (3) distilling some critical questions for advancing the field of trusted autonomy. The inquiry is augmented with conceptual models that we propose along the way by recompiling and reshaping the literature into forms that enables trusted autonomous systems to become a reality. The paper offers a vision for a Trusted Cyborg Swarm, an extension of our previous Cognitive Cyber Symbiosis concept, whereby humans and machines meld together in a harmonious, seamless, and coordinated manner. A Review of Theoretical and Practical Challenges of Trusted Autonomy in Big Data

Our recent addition to the NLP R universe is called R package ruimtehol which is open sourced at https://github.com/bnosac/ruimtehol This R package is a wrapper around Starspace which provides a neural embedding model for doing the following on text:

We at STATWORX work a lot with R and we often use the same little helper functions within our projects. These functions ease our daily work life by reducing repetitive code parts or by creating overviews of our projects. At first, there was no plan to make a package, but soon I realised, that it will be much easier to share and improve those functions, if they are within a package. Up till the 24th December I will present one function each day from helfRlein. So, on the 4th day of Christmas my true love gave to me…

By George Seif, AI / Machine Learning Engineer

Even though machine learning (ML) has been around for decades, it seems that in the last year, much of the news (notably in mainstream media) surrounding it has turned to interpretability - including ideas like trust, the ML black box, and fairness or ethics. Surely, if the topic is growing in popularity, that must mean it’s important. But why, exactly - and to whom?

Download this chapter from Data Mining Techniques, Third Edition, by Gordon Linoff and Michael Berry, and learn how to create derived variables, which allow the statistical modeling process to incorporate human insights. As much art as science, selecting variables for modeling is “one of the most creative parts of the data mining process,” according to the authors.

spatsoc is an R package written by Alec Robitaille, Quinn Webber and Eric Vander Wal of the Wildlife Evolutionary Ecology Lab (WEEL) at Memorial University of Newfoundland. It is the lab’s first R package and was recently accepted through the rOpenSci onboarding process with a big thanks to reviewers Priscilla Minotti and Filipe Teixeira, and editor Lincoln Mullen.