A machine learning algorithm isn't worth much without great training data to power it. After all, algorithms learn from data, discovering relationships, developing understanding, making decisions, and evaluating their confidence from the training data they're given. And the better the training data is, the better the model performs. In fact, the quality and quantity of your training data has as much to do with the success of your data project as the algorithms themselves. Join us for this latest Data Science Central webinar on the basics of training data where we will cover: What training data is and why it's so important What training data looks like for a variety of projects Why training data should be labeled and how to get it labeled How much training data you need Speaker: Jennifer Prendki, VP of Machine Learning -- Figure Eight Hosted by: Bill Vorhies, Editorial Director -- Data Science Central

Big data, data science, deep learning, artificial intelligence are the key words of intense hype related with a job market in full evolution, that impose to adapt the contents of our university professional trainings. Which artificial intelligence is mostly concerned by the job offers? Which methodologies and technologies should be favored in the training pprograms? Which objectives, tools and educational resources do we needed to put in place to meet these pressing needs? We answer these questions in describing the contents and operational ressources in the Data Science orientation of the speciality Applied Mathematics at INSA Toulouse. We focus on basic mathematics training (Optimization, Probability, Statistics), associated with the practical implementation of the most performing statistical learning algorithms, with the most appropriate technologies and on real examples. Considering the huge volatility of the technologies, it is imperative to train students in seft-training, this will be their technological watch tool when they will be in professional activity. This explains the structuring of the educational site https://github.com/wikistat/ into a set of tutorials. Finally, to motivate the thorough practice of these tutorials, a serious game is organized each year in the form of a prediction contest between students of Master degrees in Applied Mathematics for IA.

In recent years, there has been a lot of focus on adaptive e-learning, fueled by the advances of machine learning and artificial intelligence. As the one-size-fits-all approach of e-learning loses its appeal and online course attrition rates continue to rise, there is a move toward more personalized and adaptive learning to engage learners and achieve better learning outcomes. Personalized and adaptive learning has the ability to change learning content or the mode of delivery on the fly and to provide real-time feedback to learners. The origin of adaptive learning came from the research of intelligent tutoring systems, recommender systems and adaptive hypermedia. The advent of machine learning and artificial intelligence techniques have helped the plethora of platforms and tools that support adaptive learning flourish.

The course, recorded at the University of San Francisco as part of the Masters of Science in Data Science curriculum, covers the most important practical foundations for modern machine learning. There are 12 lessons, each of which is around two hours long--a list of all the lessons along with a screenshot from each is at the end of this post. There are some excellent machine learning courses already, most notably the wonderful Coursera course from Andrew Ng. But that course is showing its age now, particularly since it uses Matlab for coursework. This new course uses modern tools and libraries, including python, pandas, scikit-learn, and pytorch.

"The general public has become quite aware of AI and the impact it can have on health care outcomes such as providing clinicians with improved diagnostics. However, if medical education does not begin to teach medical students about AI and how to apply it into patient care then the advancement of technology will be limited in use and its impact on patient care," explained corresponding author Vijaya B. Kolachalama, PhD, assistant professor of medicine at Boston University School of Medicine (BUSM). Using a PubMed search with'machine learning' as the medical subject heading term, the researchers found that the number of papers published in the area of ML has increased since the beginning of this decade. In contrast, the number of publications related to undergraduate and graduate medical education have remained relatively unchanged since 2010. Realizing the need for educating the students and trainees within the Boston University Medical Campus about ML, Kolachalama designed and taught an introductory course at BUSM.

BigML and the Qatar Computing Research Institute (QCRI), part of Hamad Bin Khalifa University, bring the first edition of our Machine Learning School to Doha, the MLSD18. This event will be one of the first activities to be hosted by QCRI's new Qatar Center for Artificial Intelligence (QCAI). QCAI's mission is to help Qatar realize its vision of becoming a knowledge-based economy by developing and promoting cutting-edge AI innovations for the betterment of human society. We will hold a two-day crash course ideal for business leaders, industry practitioners, developers, graduate students, as well as advanced undergraduates, seeking a quick, practical, and hands-on introduction to Machine Learning to solve real-world problems. The MLSD18 will help attendees to understand how to work in this new wave of innovation that is changing the face of all sectors of the economy.

Online class imbalance learning constitutes a new problem and an emerging research topic that focusses on the challenges of online learning under class imbalance and concept drift. Class imbalance deals with data streams that have very skewed distributions while concept drift deals with changes in the class imbalance status. Little work exists that addresses these challenges and in this paper we introduce queue-based resampling, a novel algorithm that successfully addresses the co-existence of class imbalance and concept drift. The central idea of the proposed resampling algorithm is to selectively include in the training set a subset of the examples that appeared in the past. Results on two popular benchmark datasets demonstrate the effectiveness of queue-based resampling over state-of-the-art methods in terms of learning speed and quality.

This document is designed to be a first-year graduate-level introduction to probabilistic programming. It not only provides a thorough background for anyone wishing to use a probabilistic programming system, but also introduces the techniques needed to design and build these systems. It is aimed at people who have an undergraduate-level understanding of either or, ideally, both probabilistic machine learning and programming languages. We start with a discussion of model-based reasoning and explain why conditioning as a foundational computation is central to the fields of probabilistic machine learning and artificial intelligence. We then introduce a simple first-order probabilistic programming language (PPL) whose programs define static-computation-graph, finite-variable-cardinality models. In the context of this restricted PPL we introduce fundamental inference algorithms and describe how they can be implemented in the context of models denoted by probabilistic programs. In the second part of this document, we introduce a higher-order probabilistic programming language, with a functionality analogous to that of established programming languages. This affords the opportunity to define models with dynamic computation graphs, at the cost of requiring inference methods that generate samples by repeatedly executing the program. Foundational inference algorithms for this kind of probabilistic programming language are explained in the context of an interface between program executions and an inference controller. This document closes with a chapter on advanced topics which we believe to be, at the time of writing, interesting directions for probabilistic programming research; directions that point towards a tight integration with deep neural network research and the development of systems for next-generation artificial intelligence applications.

Standard artificial neural networks suffer from the well-known issue of catastrophic forgetting, making continual or lifelong learning problematic. Recently, numerous methods have been proposed for continual learning, but due to differences in evaluation protocols it is difficult to directly compare their performance. To enable more meaningful comparisons, we identified three distinct continual learning scenarios based on whether task identity is known and, if it is not, whether it needs to be inferred. Performing the split and permuted MNIST task protocols according to each of these scenarios, we found that regularization-based approaches (e.g., elastic weight consolidation) failed when task identity needed to be inferred. In contrast, generative replay combined with distillation (i.e., using class probabilities as "soft targets") achieved superior performance in all three scenarios. In addition, we reduced the computational cost of generative replay by integrating the generative model into the main model by equipping it with generative feedback connections. This Replay-through-Feedback approach substantially shortened training time with no or negligible loss in performance. We believe this to be an important first step towards making the powerful technique of generative replay scalable to real-world continual learning applications.

The Amazon SageMaker machine learning service is a full platform that greatly simplifies the process of training and deploying your models at scale. However, there are still major gaps to enabling data scientists to do research and development without having to go through the heavy lifting of provisioning the infrastructure and developing their own continuous delivery practices to obtain quick feedback. In this talk, you will learn how to leverage AWS CodePipeline, CloudFormation, CodeBuild, and SageMaker to create continuous delivery pipelines that allow the data scientist to use a repeatable process to build, train, test and deploy their models. Below, I've included a screencast of the talk I gave at the AWS NYC Summit in July 2018 along with a transcript (generated by Amazon Transcribe – another Machine Learning service – along with lots of human editing). The last six minutes of the talk include two demos on using SageMaker, CodePipeline, and CloudFormation as part of the open source solution we created.