This paper proposes a novel framework for fusing multi-temporal, multispectral satellite images and OpenStreetMap (OSM) data for the classification of local climate zones (LCZs). Feature stacking is the most commonly-used method of data fusion but does not consider the heterogeneity of multimodal optical images and OSM data, which becomes its main drawback. The proposed framework processes two data sources separately and then combines them at the model level through two fusion models (the landuse fusion model and building fusion model), which aim to fuse optical images with landuse and buildings layers of OSM data, respectively. In addition, a new approach to detecting building incompleteness of OSM data is proposed. The proposed framework was trained and tested using data from the 2017 IEEE GRSS Data Fusion Contest, and further validated on one additional test set containing test samples which are manually labeled in Munich and New York. Experimental results have indicated that compared to the feature stacking-based baseline framework the proposed framework is effective in fusing optical images with OSM data for the classification of LCZs with high generalization capability on a large scale. The classification accuracy of the proposed framework outperforms the baseline framework by more than 6% and 2%, while testing on the test set of 2017 IEEE GRSS Data Fusion Contest and the additional test set, respectively. In addition, the proposed framework is less sensitive to spectral diversities of optical satellite images and thus achieves more stable classification performance than state-of-the art frameworks.

Many applications of machine learning in science and medicine, including molecular property and protein function prediction, can be cast as problems of predicting some properties of graphs, where having good graph representations is critical. However, two key challenges in these domains are (1) extreme scarcity of labeled data due to expensive lab experiments, and (2) needing to extrapolate to test graphs that are structurally different from those seen during training. In this paper, we explore pre-training to address both of these challenges. In particular, working with Graph Neural Networks (GNNs) for representation learning of graphs, we wish to obtain node representations that (1) capture similarity of nodes' network neighborhood structure, (2) can be composed to give accurate graph-level representations, and (3) capture domain-knowledge. To achieve these goals, we propose a series of methods to pre-train GNNs at both the node-level and the graph-level, using both unlabeled data and labeled data from related auxiliary supervised tasks. We perform extensive evaluation on two applications, molecular property and protein function prediction. We observe that performing only graph-level supervised pre-training often leads to marginal performance gain or even can worsen the performance compared to non-pre-trained models. On the other hand, effectively combining both node- and graph-level pre-training techniques significantly improves generalization to out-of-distribution graphs, consistently outperforming non-pre-trained GNNs across 8 datasets in molecular property prediction (resp. 40 tasks in protein function prediction), with the average ROC-AUC improvement of 7.2% (resp. 11.7%).

The causes underlying unfair decision making are complex, being internalised in different ways by decision makers, other actors dealing with data and models, and ultimately by the individuals being affected by these decisions. One frequent manifestation of all these latent causes arises in the form of missing values: protected groups are more reluctant to give information that could be used against them, delicate information for some groups can be erased by human operators, or data acquisition may simply be less complete and systematic for minority groups. As a result, missing values and bias in data are two phenomena that are tightly coupled. However, most recent techniques, libraries and experimental results dealing with fairness in machine learning have simply ignored missing data. In this paper, we claim that fairness research should not miss the opportunity to deal properly with missing data. To support this claim, (1) we analyse the sources of missing data and bias, and we map the common causes, (2) we find that rows containing missing values are usually fairer than the rest, which should not be treated as the uncomfortable ugly data that different techniques and libraries get rid of at the first occasion, and (3) we study the trade-off between performance and fairness when the rows with missing values are used (either because the technique deals with them directly or by imputation methods). We end the paper with a series of recommended procedures about what to do with missing data when aiming for fair decision making.

The incorporation of macro-actions (temporally extended actions) into multi-agent decision problems has the potential to address the curse of dimensionality associated with such decision problems. Since macro-actions last for stochastic durations, multiple agents executing decentralized policies in cooperative environments must act asynchronously. We present an algorithm that modifies generalized advantage estimation for temporally extended actions, allowing a state-of-the-art policy optimization algorithm to optimize policies in Dec-POMDPs in which agents act asynchronously. We show that our algorithm is capable of learning optimal policies in two cooperative domains, one involving real-time bus holding control and one involving wildfire fighting with unmanned aircraft. Our algorithm works by framing problems as "event-driven decision processes," which are scenarios in which the sequence and timing of actions and events are random and governed by an underlying stochastic process. In addition to optimizing policies with continuous state and action spaces, our algorithm also facilitates the use of event-driven simulators, which do not require time to be discretized into time-steps. We demonstrate the benefit of using event-driven simulation in the context of multiple agents taking asynchronous actions. We show that fixed time-step simulation risks obfuscating the sequence in which closely separated events occur, adversely affecting the policies learned. In addition, we show that arbitrarily shrinking the time-step scales poorly with the number of agents.

A two-person team from the UNICEF's Office of Innovation in New York recently joined DSTI in Sierra Leone to collaborate on a Machine Learning "Hackathon" As part of efforts to develop the technology and innovation ecosystem to support development of Sierra Leone, UNICEF is collaborating with the Directorate of Science, Technology and Innovation (DSTI) in the Office of the President, on a knowledge exchange partnership, around innovative Machine Learning techniques which, it is hoped, will add value to Government's work around data for decision making in the country. A two-person team from the UNICEF's Office of Innovation in New York recently joined DSTI in Sierra Leone to collaborate on a Machine Learning "Hackathon" to work on data from the education sector in support of the Government's Free Quality School Education initiative. Officials from different Government Ministries, Departments and Agencies joined the team to enhance their knowledge of Machine Learning and advanced data analysis techniques, for use in their own areas of government. Shane O'Connor, Technology for Development Specialist at UNICEF Sierra Leone, stated that the opportunity afforded by this collaboration is huge. "With the President's establishment of the DSTI and with UNICEF's collaboration, there really is great potential for a step change in how Technology and Innovation can be leveraged to deliver for Sierra Leone," he said.

CEO at Things Foundation, Technology Manager at Let's Do It Foundation Head of Cortex Ventures- Africa's first AI only focused VC Fund

Artificial intelligence is creating opportunities for contributing to much-needed efficiency gains in the handling of data that underpins Earth system science and weather and climate predictions, WMO Secretary-General Petteri Taalas told the Artificial Intelligence (AI) for Good Global Summit. The meeting, organized by the International Telecommunications Union, seeks to identify practical applications of artificial intelligence to advance the sustainable development agenda. It brings together more than 2,000 participants from over 120 countries. "This summit is the leading United Nations platform for dialogue on artificial intelligence. AI is being used to fight hunger, mitigate the climate crisis, or facilitate the transition to smart sustainable cities," said ITU Secretary-General Houlin Zhao.

Breakthrough after breakthrough, artificial intelligence (AI) has continued to challenge the human definition of impossible. Our lives and AI technologies are intertwining further as time goes on. For us, this means a more convenient life aided by this technology. At the same time though, this means that we are making ourselves vulnerable to the consequences of the errors that AIs can commit. Of course, a 100% secure system is desirable in order to ensure the safety of humans interacting using. However, there is no such thing as a perfect security system.

Alexa's poor reputation for privacy may soon worsen as a patent filed by the firm suggests the virtual assistant may start listening before its'wake word' is said. Under the plans Alexa will be able to detect when it is being given a command even if the wake word is said at the end of the sentence instead of at the front. The move raises concerns over user privacy as Alexa will, by default, always be listening to conversations on the off-chance its wakeword is spoken. Alexa's poor reputation for privacy may soon worsen as a patent filed by the firm suggests the virtual assistant may start listening before its'wake word' is said. The patent, filed with the US Patent and Trademark Office, reveals the Seattle-fimrs plans for the next evolutionary step for it Alexa's technology.

HAL 9000, The T-800, Data, Rachael, Bishop, KITT, Agent Smith, Holly, Mia, Teddy… you can't say we weren't warned. Travel back to a smoggy November 1st 1698 and as you flicked through your morning edition of the London Gazette, you'd have read about Thomas Savery patenting a piece of futuristic, unfathomable, super-technology – the world's first steam engine. Since then, cogs, belts, valves, microchips and code have allowed us to create ever more sophisticated automated technology. The rise of the machines has been coming for centuries. What do immigrants and robots have in common?