The conference focuses on four main themes and will be augmented by additional discussions. Our key themes are structural and institutional change in gender equality in R&I; a broader concept of equality in R&I; digitalization and gender equality; and gender equality in innovation. Follow conference live stream from this link. This session will take stock of the advancement over the past 20 years of gender equality policy in European research and innovation, its achievements and continued challenges. Structural change is today the dominant approach to advancing gender equality in Research Funding and Performing Organisations in the EU.

This post is not meant for seasoned software engineers. This is geared towards data scientists and machine learning (ML) practitioners, who like me, do not come from a software engineering background. We use Python a lot for our work. It is on the way to becoming the fastest growing major language for modern data-driven analytics and artificial intelligence (AI) apps. However, it is also used for simple scripting purpose, to automate stuff, to test a hypothesis, create interactive plots for brainstorming, to control lab instruments, etc.

CHIBA – Corporate Japan's growing need to rely on new technologies to cope with a shrinking workforce was on show at the recently held CEATEC technology exhibition in the city of Chiba, with service industry companies turning out in greater numbers this year. As more and more skilled workers reach retirement across various industries in rapidly graying Japan, businesses are turning to new technologies to hand down field experience and knowledge to younger workers. East Nippon Expressway Co., operator of expressways and toll roads in Japan, is one of the companies adopting "mixed reality" technology as it seeks to boost training of inspection and maintenance personnel. "We are increasingly required by the government to conduct checks on roads but our skilled workers are aging and cannot work at their fullest anymore. So we needed to rely on high tech to share and pass on their know-how to the younger employees," said Masaki Ishiguro, official in charge of maintenance at the firm, also known as Nexco East.

Abu Dhabi on Wednesday announced the establishment of the Mohamed bin Zayed University of Artificial Intelligence (MBZUAI), the first graduate level, research-based AI university in the world. MBZUAI will enable graduate students, businesses, and governments to advance artificial intelligence, a statement said. The University is named after Sheikh Mohamed bin Zayed Al Nahyan, Crown Prince of Abu Dhabi and Deputy Supreme Commander of the UAE Armed Forces, who has long advocated for the UAE's development of human capital through knowledge and scientific thinking to take the nation into the future, it added. MBZUAI will provide all admitted students with a full scholarship, plus benefits such as a monthly allowance, health insurance, and accommodation. The university will also work with leading local and global companies to secure internships, and will also assist students in finding employment opportunities.

In the fall of 2017, Sam Bowman, a computational linguist at New York University, figured that computers still weren't very good at understanding the written word. Sure, they had become decent at simulating that understanding in certain narrow domains, like automatic translation or sentiment analysis (for example, determining if a sentence sounds "mean or nice," he said). But Bowman wanted measurable evidence of the genuine article: bona fide, human-style reading comprehension in English. So he came up with a test. In an April 2018 paper coauthored with collaborators from the University of Washington and DeepMind, the Google-owned artificial intelligence company, Bowman introduced a battery of nine reading-comprehension tasks for computers called GLUE (General Language Understanding Evaluation). The test was designed as "a fairly representative sample of what the research community thought were interesting challenges," said Bowman, but also "pretty straightforward for humans."

Researchers at University of Montreal are partnering with ed tech firm Classcraft to explore the use of artificial intelligence (AI) to measure student engagement and survey potential classroom management changes. The research will take place with data collected on Classcraft's technology, which attempts to use engagement managing tools to improve school climate, academic scores and social-emotional learning, Education Week reports. This study reflects a movement aimed at deploying AI into schools in order to improve social cultures, but critics claim the technology could deliver the wrong information, as well as leave students' personal data exposed to potential breaches, Education Week notes. The Classcraft engagement management system -- which the organization says is in place in 75,000 classrooms across 160 countries -- lets educators give points for positive, supportive behaviors including empathy. However, the software currently does not predict how the points will improve the climate, nor does it offer teachers ideas to make changes.

The notion of uncertainty is of major importance in machine learning and constitutes a key element of machine learning methodology. In line with the statistical tradition, uncertainty has long been perceived as almost synonymous with standard probability and probabilistic predictions. Yet, due to the steadily increasing relevance of machine learning for practical applications and related issues such as safety requirements, new problems and challenges have recently been identified by machine learning scholars, and these problems may call for new methodological developments. In particular, this includes the importance of distinguishing between (at least) two different types of uncertainty, often refereed to as aleatoric and epistemic. In this paper, we provide an introduction to the topic of uncertainty in machine learning as well as an overview of hitherto attempts at handling uncertainty in general and formalizing this distinction in particular. 1 Introduction Machine learning is essentially concerned with extracting models from data and using these models to make predictions.

This work investigates the framework and performance issues of the composite neural network, which is composed of a collection of pre-trained and non-instantiated neural network models connected as a rooted directed acyclic graph for solving complicated applications. A pre-trained neural network model is generally well trained, targeted to approximate a specific function. Despite a general belief that a composite neural network may perform better than a single component, the overall performance characteristics are not clear. In this work, we construct the framework of a composite network, and prove that a composite neural network performs better than any of its pre-trained components with a high probability bound. In addition, if an extra pre-trained component is added to a composite network, with high probability, the overall performance will not be degraded. In the study, we explore a complicated application---PM2.5 prediction---to illustrate the correctness of the proposed composite network theory. In the empirical evaluations of PM2.5 prediction, the constructed composite neural network models support the proposed theory and perform better than other machine learning models, demonstrate the advantages of the proposed framework.

Spiking Neural Networks (SNNs) offer a promising alternative to conventional Artificial Neural Networks (ANNs) for the implementation of on-device low-power online learning and inference. On-device training is, however, constrained by the limited amount of data available at each device. In this paper, we propose to mitigate this problem via cooperative training through Federated Learning (FL). To this end, we introduce an online FL-based learning rule for networked on-device SNNs, which we refer to as FL-SNN. FL-SNN leverages local feedback signals within each SNN, in lieu of backpropagation, and global feedback through communication via a base station. The scheme demonstrates significant advantages over separate training and features a flexible trade-off between communication load and accuracy via the selective exchange of synaptic weights.

In the learning to learn (L2L) framework, we cast the design of optimization algorithms as a machine learning problem and use deep neural networks to learn the update rules. In this paper, we extend the L2L framework to zeroth-order (ZO) optimization setting, where no explicit gradient information is available. Our learned optimizer, modeled as recurrent neural network (RNN), first approximates gradient by ZO gradient estimator and then produces parameter update utilizing the knowledge of previous iterations. To reduce high variance effect due to ZO gradient estimator, we further introduce another RNN to learn the Gaussian sampling rule and dynamically guide the query direction sampling. Our learned optimizer outperforms hand-designed algorithms in terms of convergence rate and final solution on both synthetic and practical ZO optimization tasks (in particular, the black-box adversarial attack task, which is one of the most widely used tasks of ZO optimization). We finally conduct extensive analytical experiments to demonstrate the effectiveness of our proposed optimizer. Learning to learn (L2L) is a recently proposed meta-learning framework where we leverage deep neural networks to learn optimization algorithms automatically. The most common choice for the learned optimizer is recurrent neural network (RNN) since it can capture long-term dependencies and propose parameter updates based on knowledge of previous iterations. By training RNN op-timizers on predefined optimization tasks, the optimizers are capable of learning to explore the loss landscape and adaptively choose descent directions and steps (Lv et al., 2017).