The use of delivery services is an increasing trend worldwide, further enhanced by the COVID pandemic. In this context, drone delivery systems are of great interest as they may allow for faster and cheaper deliveries. This paper presents a navigation system that makes feasible the delivery of parcels with autonomous drones. The system generates a path between a start and a final point and controls the drone to follow this path based on its localization obtained through GPS, 9DoF IMU, and barometer. In the landing phase, information of poses estimated by a marker (ArUco) detection technique using a camera, ultra-wideband (UWB) devices, and the drone's software estimation are merged by utilizing an Extended Kalman Filter algorithm to improve the landing precision. A vector field-based method controls the drone to follow the desired path smoothly, reducing vibrations or harsh movements that could harm the transported parcel. Real experiments validate the delivery strategy and allow to evaluate the performance of the adopted techniques. Preliminary results state the viability of our proposal for autonomous drone delivery.

Self-supervised learning (SSL) of energy based models has an intuitive relation to equilibrium thermodynamics because the softmax layer, mapping energies to probabilities, is a Gibbs distribution. However, in what way SSL is a thermodynamic process? We show that some SSL paradigms behave as a thermodynamic composite system formed by representations and self-labels in contact with a nonequilibrium reservoir. Moreover, this system is subjected to usual thermodynamic cycles, such as adiabatic expansion and isochoric heating, resulting in a generalized Gibbs ensemble (GGE). In this picture, we show that learning is seen as a demon that operates in cycles using feedback measurements to extract negative work from the system. As applications, we examine some SSL algorithms using this idea.

Ontologies are increasingly used for machine reasoning over the last few years. They can provide explanations of concepts or be used for concept classification if there exists a mapping from the desired labels to the relevant ontology. Another advantage of using ontologies is that they do not need a learning process, meaning that we do not need the train data or time before using them. This paper presents a practical use of an ontology for a classification problem from the financial domain. It first transforms a given ontology to a graph and proceeds with generalization with the aim to find common semantic descriptions of the input sets of financial concepts. We present a solution to the shared task on Learning Semantic Similarities for the Financial Domain (FinSim-2 task). The task is to design a system that can automatically classify concepts from the Financial domain into the most relevant hypernym concept in an external ontology - the Financial Industry Business Ontology. We propose a method that maps given concepts to the mentioned ontology and performs a graph search for the most relevant hypernyms. We also employ a word vectorization method and a machine learning classifier to supplement the method with a ranked list of labels for each concept.

We demonstrate that frequently appearing objects can be discovered by training randomly sampled patches from a small number of images (100 to 200) by self-supervision. Key to this approach is the pattern space, a latent space of patterns that represents all possible sub-images of the given image data. The distance structure in the pattern space captures the co-occurrence of patterns due to the frequent objects. The pattern space embedding is learned by minimizing the contrastive loss between randomly generated adjacent patches. To prevent the embedding from learning the background, we modulate the contrastive loss by color-based object saliency and background dissimilarity. The learned distance structure serves as object memory, and the frequent objects are simply discovered by clustering the pattern vectors from the random patches sampled for inference. Our image representation based on image patches naturally handles the position and scale invariance property that is crucial to multi-object discovery. The method has been proven surprisingly effective, and successfully applied to finding multiple human faces and bodies from natural images.

Bengaluru: Global professional services company Accenture will acquire umlaut, an engineering consulting and services firm headquartered in Aachen, Germany for an undisclosed amount. The acquisition will scale Accenture's deep engineering capabilities to help companies use digital technologies like cloud, artificial intelligence, and 5G to transform how they design, engineer and manufacture their products as well as embed sustainability. The acquisition of umlaut will add more than 4,200 industry-leading engineers and consultants across 17 countries to Accenture's Industry X services, and expand the company's capabilities across a range of industries, including automotive, aerospace & defense, telecommunications, energy and utilities, Accenture said in a statement. Industry X combines Accenture's powerful data and digital capabilities with deep engineering expertise to offer clients the broadest suite of services for digitizing their engineering functions, factory floors and plant operations, improving productivity, speeding up the transformation of hardware into software-enabled products, and allowing for faster and more flexible product development. "We predicted that digital would ultimately be applied at scale to the core of a company's business - the design, engineering and manufacturing of their products. And, for nearly a decade Accenture has been building the unique capabilities and ecosystem partnerships to combine the power of digital with traditional engineering services," said Julie Sweet, chief executive officer, Accenture.

Artificial intelligence (AI) has quickened its progress in 2021. A new administration is in place in the US and the talk is about a major push for Green Technology and the need to stimulate next generation infrastructure including AI and 5G to generate economic recovery with David Knight forecasting that 5G has the potential - the potential - to drive GDP growth of 40% or more by 2030. The Biden administration has stated that it will boost spending in emerging technologies that includes AI and 5G to $300Bn over a four year period. On the other side of the Atlantic Ocean, the EU have announced a Green Deal and also need to consider the European AI policy to develop next generation companies that will drive economic growth and employment. It may well be that the EU and US (alongside Canada and other allies) will seek ways to work together on issues such as 5G policy and infrastructure development. The UK will be hosting COP 26 and has also made noises about AI and 5G development.

The Earth's core is growing lopsided, scientists have discovered, but it is unclear why. The solid-iron core in the middle of the planet has been growing faster under Indonesia's Banda Sea, seismologists at the University of California in Berkeley found. The growth on one side of the molten metal is the product of iron crystals that form as the molten iron cools, but something in the Earth's outer core or mantle under the south Asian country is removing heat at a faster rate than on the opposite side, under Brazil. The faster the cooling, the faster that iron crystallisation occurs – and the faster the growth increases. Such a disparity has significant implications for the Earth's magnetic field, and the convection currents in the core that generate the field are what protects us from dangerous solar particles.

Nowadays, Graph Neural Networks (GNNs) following the Message Passing paradigm become the dominant way to learn on graphic data. Models in this paradigm have to spend extra space to look up adjacent nodes with adjacency matrices and extra time to aggregate multiple messages from adjacent nodes. To address this issue, we develop a method called LinkDist that distils self-knowledge from connected node pairs into a Multi-Layer Perceptron (MLP) without the need to aggregate messages. Experiment with 8 real-world datasets shows the MLP derived from LinkDist can predict the label of a node without knowing its adjacencies but achieve comparable accuracy against GNNs in the contexts of semi- and full-supervised node classification. Moreover, LinkDist benefits from its Non-Message Passing paradigm that we can also distil self-knowledge from arbitrarily sampled node pairs in a contrastive way to further boost the performance of LinkDist.

Inter-agent communication can significantly increase performance in multi-agent tasks that require co-ordination to achieve a shared goal. Prior work has shown that it is possible to learn inter-agent communication protocols using multi-agent reinforcement learning and message-passing network architectures. However, these models use an unconstrained broadcast communication model, in which an agent communicates with all other agents at every step, even when the task does not require it. In real-world applications, where communication may be limited by system constraints like bandwidth, power and network capacity, one might need to reduce the number of messages that are sent. In this work, we explore a simple method of minimizing communication while maximizing performance in multi-task learning: simultaneously optimizing a task-specific objective and a communication penalty. We show that the objectives can be optimized using Reinforce and the Gumbel-Softmax reparameterization. We introduce two techniques to stabilize training: 50% training and message forwarding. Training with the communication penalty on only 50% of the episodes prevents our models from turning off their outgoing messages. Second, repeating messages received previously helps models retain information, and further improves performance. With these techniques, we show that we can reduce communication by 75% with no loss of performance.

Large-scale pre-trained models (PTMs) such as BERT and GPT have recently achieved great success and become a milestone in the field of artificial intelligence (AI). Owing to sophisticated pre-training objectives and huge model parameters, large-scale PTMs can effectively capture knowledge from massive labeled and unlabeled data. By storing knowledge into huge parameters and fine-tuning on specific tasks, the rich knowledge implicitly encoded in huge parameters can benefit a variety of downstream tasks, which has been extensively demonstrated via experimental verification and empirical analysis. It is now the consensus of the AI community to adopt PTMs as backbone for downstream tasks rather than learning models from scratch. In this paper, we take a deep look into the history of pre-training, especially its special relation with transfer learning and self-supervised learning, to reveal the crucial position of PTMs in the AI development spectrum. Further, we comprehensively review the latest breakthroughs of PTMs. These breakthroughs are driven by the surge of computational power and the increasing availability of data, towards four important directions: designing effective architectures, utilizing rich contexts, improving computational efficiency, and conducting interpretation and theoretical analysis. Finally, we discuss a series of open problems and research directions of PTMs, and hope our view can inspire and advance the future study of PTMs.