Microsoft Corp. has launched a new series of online courses for executives to learn about AI, as it tries to help businesses catch up to the trend of AI in business. AI Business School is a free course to educate executives about the advantages of integrating AI into their business and how to prepare their staff for the advancements it provides. Microsoft already offers similar courses for developers (AI School) and engineers (Microsoft Professional Program for Artificial Intelligence), but AI Business School will be the first of its kind for executives; as it is geared much more towards the organizational and operational aspects of implementing AI than the previous courses, which were centred around the more technical aspects of AI. The course will focus on four main areas: culture, strategy, responsible AI, and technology. A Microsoft blog post carried an endorsement from Edmund Monk, chief executive of the leading membership body for learning professionals, the Learning and Performance Institute.

Off-Policy reinforcement learning (RL) is an important class of methods for many problem domains, such as robotics, where the cost of collecting data is high and on-policy methods are consequently intractable. Standard methods for applying Q-learning to continuous-valued action domains involve iteratively sampling the Q-function to find a good action (e.g. via hill-climbing), or by learning a policy network at the same time as the Q-function (e.g. DDPG). Both approaches make tradeoffs between stability, speed, and accuracy. We propose a novel approach, called Cross-Entropy Guided Policies, or CGP, that draws inspiration from both classes of techniques. CGP aims to combine the stability and performance of iterative sampling policies with the low computational cost of a policy network. Our approach trains the Q-function using iterative sampling with the Cross-Entropy Method (CEM), while training a policy network to imitate CEM's sampling behavior. We demonstrate that our method is more stable to train than state of the art policy network methods, while preserving equivalent inference time compute costs, and achieving competitive total reward on standard benchmarks.

Network embedding is the process of learning low-dimensional representations for nodes in a network, while preserving node features. Existing studies only leverage network structure information and focus on preserving structural features. However, nodes in real-world networks often have a rich set of attributes providing extra semantic information. It has been demonstrated that both structural and attribute features are important for network analysis tasks. To preserve both features, we investigate the problem of integrating structure and attribute information to perform network embedding and propose a Multimodal Deep Network Embedding (MDNE) method. MDNE captures the non-linear network structures and the complex interactions among structures and attributes, using a deep model consisting of multiple layers of non-linear functions. Since structures and attributes are two different types of information, a multimodal learning method is adopted to pre-process them and help the model to better capture the correlations between node structure and attribute information. We employ both structural proximity and attribute proximity in the loss function to preserve the respective features and the representations are obtained by minimizing the loss function. Results of extensive experiments on four real-world datasets show that the proposed method performs significantly better than baselines on a variety of tasks, which demonstrate the effectiveness and generality of our method.

We present a novel optimizer for deep neural networks that combines the ideas of Netwon's method and line search to efficiently compute and utilize curvature information. Our work is based on empirical observation suggesting that the loss function can be approximated by a parabola in negative gradient direction. Due to this approximation, we are able to perform a variable and loss function dependent parameter update by jumping directly into the minimum of the approximated parabola. To evaluate our optimizer, we performed multiple comprehensive hyperparameter grid searches for which we trained more than 20000 networks in total. We can show that PAL outperforms RMSPROP, and can outperform gradient descent with momentum and ADAM on large-scale high-dimensional machine learning problems. Furthermore, PAL requires up to 52.2% less training epochs. PyTorch and TensorFlow implementations are provided at https://github.com/cogsys-tuebingen/PAL.

Last December, entrepreneur Amin Khoury gave Northeastern University's College of Computer Science a $50 million gift. The money was slated for programs that would help new graduates compete in a marketplace increasingly dominated by artificial intelligence and automation. The university's press release touted, "As the global economy adapts to the influence of artificial intelligence … Northeastern is empowering humans to be agile learners, thinkers, and creators, beyond the capacity of any machine." The school, like quite a few others, is reimagining itself as an incubator for skills that are difficult to automate: creativity, imagination, mental flexibility. Indeed, Joseph Aoun, Northeastern's president, literally wrote the book on this.

Some artificial intelligences can perform tasks with superhuman ability, but just how clever are they overall? A competition called the Animal-AI Olympics will pit AIs against tests normally used to study animal intelligence. From April, AIs will battle it out in a virtual playground for a $10,000 prize pool. All the tasks involve retrieving a piece of food, but the skills needed to succeed vary in complexity.

In this article, I'm interviewing a veteran data scientist, Dr Stylianos (Stelios) Kampakis, about his career to date and how he helps decision makers across a range of businesses understand how data science can benefit them. While data science is a field showing immense growth at present, it's somewhat nebulous in its description. I think there's a lot of uncertainty as to exactly what it is and how to apply it. Fortunately, Stelios is an expert data scientist with a mission to educate the public about the power of data science and AI. He is a member of the Royal Statistical Society, honorary research fellow at the UCL Centre for Blockchain Technologies and CEO of The Tesseract Academy.

Informatics for all is a coalition whose aim is to establish informatics as a fundamental discipline to be taken by all students in school. Informatics should be seen as important as mathematics, the sciences, and the various languages. It should be recognized by all as a truly foundational discipline that plays a significant role in education for the 21st century. In Europe, education is a matter left to the individual states. However, education, competencies, and preparedness of the workforce are all important matters for the European Union (EU).

Europe is not a static entity but here is what it looks like in 2019: The European Union is made up of 28 countries. The capital is in Brussels, Belgium, and the presidency is shared among EU members each semester. In 2019, the first semester sees Romania holding presidency until June, then Finland until the end of the year. An estimated 551.8 million people live in the EU, speaking 24 official languages. Approximately 72% of the population is employed,a which is greater than the pre-economic-crisis peak of 2008.

These are the working definitions that most of us find adequate in daily life and daily computer science. To consider whether there is more to it is to consider an ontology, the ontology of the variable. Is there a good comprehensive definition of "variable" for students and laypersons? First, however, let's address the subject that arises prominently where variables meet worldly ontology--the professional design of an ontology for some real thing, in some domain, driven by a commercial need to capture some enterprise in a database. The question is, "What do we need to keep track of?"