We live in a connected world and generate a vast amount of connected data. Social networks, financial transaction systems, biological networks, transportation systems, and a telecommunication nexus are all examples. The paper citation network displayed in Figure 1 is another example of connected data. The nodes represent research papers, while the edges illustrate citations between papers, with the various colour indicative of a report's subject, with seven colours coding seven topics. Representing connected data is possible using a graph data structure regularly used in Computer Science.

Spam filtering, face recognition, recommendation engines -- when you have a large data set on which you'd like to perform predictive analysis or pattern recognition, machine learning is the way to go. The proliferation of free open source software has made machine learning easier to implement both on single machines and at scale, and in most popular programming languages. These open source tools include libraries for the likes of Python, R, C, Java, Scala, Clojure, JavaScript, and Go. Apache Mahout provides a way to build environments for hosting machine learning applications that can be scaled quickly and efficiently to meet demand. Mahout works mainly with another well-known Apache project, Spark, and was originally devised to work with Hadoop for the sake of running distributed applications, but has been extended to work with other distributed back ends like Flink and H2O. Mahout uses a domain specific language in Scala.

The economic recession that follows as a consequence of the Covid-19 crisis and in particular the demise of certain sectors of the economy (physical retail, hospitality sector, etc) means that there will be greater pressure on politicians around the world to consider how to stimulate GPD growth in the post-pandemic world. However, there are also increasing pressures on politicians to combat the threat posed by Climate Change. Are the desired objectives of GDP and employment growth as well as reducing pollution at odds with each other? What if there is a pathway to GDP growth with the creation of new jobs and yet at the same time we are able to reduce emissions of Green House Gasses (GHGs)? A report entitled "How AI can enable a sustainable future" by PWC and commissioned by Microsoft (lead authors Celine Herweijer of PWC and Lucas Joppa of Microsoft) estimates that using AI for environmental applications across four sectors – agriculture, water, energy and transport. The report estimated that such applications could contribute up to $5.2 trillion USD to the global economy in 2030, a 4.4% increase relative to business as usual.

On Nov 28th 2019, the EU parliament declared a global climate and environmental emergency. They say that all politics is local and across the world climate change seems to be coming home to roost. In the hills around San Francisco the bankrupt PG&E power company pre-emptively shutoff power to homes for several days as it worried that its ageing electrical equipment would act as a match to the parched trees and vegetation. In Europe extreme flooding has been immersing ancient towns in apocalyptic scenes. In Australia it was hard to discern the iconic Sydney Opera House for all the smoke from the raging bush fires.

Reinforcement Learning algorithms require a large number of samples to solve complex tasks with sparse and delayed rewards. Complex tasks can often be hierarchically decomposed into sub-tasks. A step in the Q-function can be associated with solving a sub-task, where the expectation of the return increases. RUDDER has been introduced to identify these steps and then redistribute reward to them, thus immediately giving reward if sub-tasks are solved. Since the problem of delayed rewards is mitigated, learning is considerably sped up. However, for complex tasks, current exploration strategies as deployed in RUDDER struggle with discovering episodes with high rewards. Therefore, we assume that episodes with high rewards are given as demonstrations and do not have to be discovered by exploration. Typically the number of demonstrations is small and RUDDER's LSTM model as a deep learning method does not learn well. Hence, we introduce Align-RUDDER, which is RUDDER with two major modifications. First, Align-RUDDER assumes that episodes with high rewards are given as demonstrations, replacing RUDDER's safe exploration and lessons replay buffer. Second, we replace RUDDER's LSTM model by a profile model that is obtained from multiple sequence alignment of demonstrations. Profile models can be constructed from as few as two demonstrations as known from bioinformatics. Align-RUDDER inherits the concept of reward redistribution, which considerably reduces the delay of rewards, thus speeding up learning. Align-RUDDER outperforms competitors on complex artificial tasks with delayed reward and few demonstrations. On the MineCraft ObtainDiamond task, Align-RUDDER is able to mine a diamond, though not frequently. Github: https://github.com/ml-jku/align-rudder, YouTube: https://youtu.be/HO-_8ZUl-UY

This performance in a variety of machine learning is because for a GMM, not all Gaussian centers tasks, such as machine translation (Vaswani et al., (lower layer neurons) are required to contribute in 2017; Dehghani et al., 2019), language modeling generating output data (upper layer neurons). The (Devlin et al., 2019; Yang et al., 2019), summarization information of the centers that do not generate data (Cohan et al., 2018; Goodman et al., 2019), is lost after observing the data. This "explainingaway" dialog (Mazaré et al., 2018; Cheng et al., 2019), effect is related to the one in the directed image captioning (Sharma et al., 2018; Zhao et al., graphical model, in the sense that the existence of 2019), and visual question answering (Yu et al., the few contributed lower neurons "explain away" 2019b; Tan and Bansal, 2019). One of the most important the other muted lower neurons on generating upper components of the Transformer architecture neurons. is its self-attention mechanism, applied universally In order to compensate for this, we describe to both the encoder and the decoder components.

Distributionally-robust optimization is often studied for a fixed set of distributions rather than time-varying distributions that can drift significantly over time (which is, for instance, the case in finance and sociology due to underlying expansion of economy and evolution of demographics). This motivates understanding conditions on probability distributions, using the Wasserstein distance, that can be used to model time-varying environments. We can then use these conditions in conjunction with online stochastic optimization to adapt the decisions. We considers an online proximal-gradient method to track the minimizers of expectations of smooth convex functions parameterised by a random variable whose probability distributions continuously evolve over time at a rate similar to that of the rate at which the decision maker acts. We revisit the concepts of estimation and tracking error inspired by systems and control literature and provide bounds for them under strong convexity, Lipschitzness of the gradient, and bounds on the probability distribution drift. Further, noting that computing projections for a general feasible sets might not be amenable to online implementation (due to computational constraints), we propose an exact penalty method. Doing so allows us to relax the uniform boundedness of the gradient and establish dynamic regret bounds for tracking and estimation error. We further introduce a constraint-tightening approach and relate the amount of tightening to the probability of satisfying the constraints.

Optimal transport is a machine learning problem with applications including distribution comparison, feature selection, and generative adversarial networks. In this paper, we propose feature-robust optimal transport (FROT) for high-dimensional data, which solves high-dimensional OT problems using feature selection to avoid the curse of dimensionality. Specifically, we find a transport plan with discriminative features. To this end, we formulate the FROT problem as a min--max optimization problem. We then propose a convex formulation of the FROT problem and solve it using a Frank--Wolfe-based optimization algorithm, whereby the subproblem can be efficiently solved using the Sinkhorn algorithm. Since FROT finds the transport plan from selected features, it is robust to noise features. To show the effectiveness of FROT, we propose using the FROT algorithm for the layer selection problem in deep neural networks for semantic correspondence. By conducting synthetic and benchmark experiments, we demonstrate that the proposed method can find a strong correspondence by determining important layers. We show that the FROT algorithm achieves state-of-the-art performance in real-world semantic correspondence datasets.

The problem of segregating recyclable waste is fairly daunting for many countries. This article presents an approach for image based classification of plastic waste using one-shot learning techniques. The proposed approach exploits discriminative features generated via the siamese and triplet loss convolutional neural networks to help differentiate between 5 types of plastic waste based on their resin codes. The approach achieves an accuracy of 99.74% on the WaDaBa Database

We propose a vision for directing research and education in the ICT field. Our Smart and Sustainable World vision targets at prosperity for the people and the planet through better awareness and control of both human-made and natural environment. The needs of the society, individuals, and industries are fulfilled with intelligent systems that sense their environment, make proactive decisions on actions advancing their goals, and perform the actions on the environment. We emphasize artificial intelligence, feedback loops, human acceptance and control, intelligent use of basic resources, performance parameters, mission-oriented interdisciplinary research, and a holistic systems view complementing the conventional analytical reductive view as a research paradigm especially for complex problems. To serve a broad audience, we explain these concepts and list the essential literature. We suggest planning research and education by specifying, in a step-wise manner, scenarios, performance criteria, system models, research problems and education content, resulting in common goals and a coherent project portfolio as well as education curricula. Research and education produce feedback to support evolutionary development and encourage creativity in research. Finally, we propose concrete actions for realizing this approach.