In this article, we propose the Artificial Intelligence Security Taxonomy to systematize the knowledge of threats, vulnerabilities, and security controls of machine-learning-based (ML-based) systems. We first classify the damage caused by attacks against ML-based systems, define ML-specific security, and discuss its characteristics. Next, we enumerate all relevant assets and stakeholders and provide a general taxonomy for ML-specific threats. Then, we collect a wide range of security controls against ML-specific threats through an extensive review of recent literature. Finally, we classify the vulnerabilities and controls of an ML-based system in terms of each vulnerable asset in the system's entire lifecycle.

Many types of data from fields including natural language processing, computer vision, and bioinformatics, are well represented by discrete, compositional structures such as trees, sequences, or matchings. Latent structure models are a powerful tool for learning to extract such representations, offering a way to incorporate structural bias, discover insight about the data, and interpret decisions. However, effective training is challenging, as neural networks are typically designed for continuous computation. This text explores three broad strategies for learning with discrete latent structure: continuous relaxation, surrogate gradients, and probabilistic estimation. Our presentation relies on consistent notations for a wide range of models. As such, we reveal many new connections between latent structure learning strategies, showing how most consist of the same small set of fundamental building blocks, but use them differently, leading to substantially different applicability and properties.

Computer Vision developments are enabling significant advances in many fields, including sports. Many applications built on top of Computer Vision technologies, such as tracking data, are nowadays essential for every top-level analyst, coach, and even player. In this paper, we survey Computer Vision techniques that can help many sports-related studies gather vast amounts of data, such as Object Detection and Pose Estimation. We provide a use case for such data: building a model for shot speed estimation with pose data obtained using only Computer Vision models. Our model achieves a correlation of 67%. The possibility of estimating shot speeds enables much deeper studies about enabling the creation of new metrics and recommendation systems that will help athletes improve their performance, in any sport. The proposed methodology is easily replicable for many technical movements and is only limited by the availability of video data.

Over the last decade, the use of robots in production and daily life has increased. With increasingly complex tasks and interaction in different environments including humans, robots are required a higher level of autonomy for efficient deliberation. Task planning is a key element of deliberation. It combines elementary operations into a structured plan to satisfy a prescribed goal, given specifications on the robot and the environment. In this manuscript, we present a survey on recent advances in the application of logic programming to the problem of task planning. Logic programming offers several advantages compared to other approaches, including greater expressivity and interpretability which may aid in the development of safe and reliable robots. We analyze different planners and their suitability for specific robotic applications, based on expressivity in domain representation, computational efficiency and software implementation. In this way, we support the robotic designer in choosing the best tool for his application.

The following article is an extended abstract submitted as part of AAAI's Faculty Highlights Program. This article summarizes the New Faculty Highlights talk with the same title at AAAI 2021. Intelligent agents such as different types of robots will soon become an integral part of our daily lives. In real-world multi-agent systems, the most fundamental challenges are assigning tasks to multiple agents and planning collision-free paths for the agents. This article surveys four directions of our research on using intelligent planning techniques for the above coordination problems.

This blog is the first of a two-part series that will provide a detailed overview of the state-of-art deep learning model DeepAR and a comparison of it to the state-of-art classical method Fb-Prophet. Whereas the second article explores a use case based end to end implementation of DeepAR algorithm in AWS sagemaker. DeepAR is a forecasting methodology based on AR RNN that learns a global model instead of fitting separate models for each time series like in other classical models. It learns from the historical data of all time-series in the dataset and produces accurate probabilistic forecasts. The technique was developed by Amazon and stands out for its ability to "scale" using multiple covariates.

In this section, we provide a brief overview of some well-known TGL methods in the literature. There exist two main broad classes of methods for learning on Continuous-Time Dynamic Graphs (CTDGs): Temporal Graph Networks and Walk Aggregating methods. For more details on the formulation of CTDGs, see this survey by Kazemi et al. Temporal Graph Networks (TGNs) generalize Message Passing Neural Networks (MPNNs) to temporal graphs. They do so by introducing a node memory which represents the state of the node at a given time, acting as a compressed representation of the node's past interactions.

Companies that are offering products and services to other businesses instead of consumers tend to take a different approach when it comes to generating demand. In order to grow at a sufficient rate, companies really have to put out all the stops because of the fact that this is the sort of thing that could potentially end up making them more competitive in the market. With all of that having been said and now out of the way, it is important to note that around 85% of all companies tend to use chatbots to generate this demand. This information comes out of a survey that was recently published by Botco AI, and it shows just how critical chatbots are to the growth strategies of B2B concerns. The people that responded to this survey stated that chatbots help them to understand their customers better than might have been the case otherwise.

Automated Driving Systems (ADS) open up a new domain for the automotive industry and offer new possibilities for future transportation with higher efficiency and comfortable experiences. However, autonomous driving under adverse weather conditions has been the problem that keeps autonomous vehicles (AVs) from going to level 4 or higher autonomy for a long time. This paper assesses the influences and challenges that weather brings to ADS sensors in an analytic and statistical way, and surveys the solutions against inclement weather conditions. State-of-the-art techniques on perception enhancement with regard to each kind of weather are thoroughly reported. External auxiliary solutions, weather conditions coverage in currently available datasets, simulators, and experimental facilities with weather chambers are distinctly sorted out. Additionally, potential future ADS sensors candidates and approaches beyond common senses are provided. By looking into all kinds of major weather problems the autonomous driving field is currently facing, and reviewing both hardware and computer science solutions in recent years, this survey points out the main moving trends of adverse weather problems in autonomous driving, i.e., advanced sensor fusions, more sophisticated networks, and V2X & IoT technologies; and also the limitations brought by emerging 1550 nm LiDARs. In general, this work contributes a holistic overview of the obstacles and directions of ADS development in terms of adverse weather driving conditions.

There are many computer vision applications including object segmentation, classification, object detection, and reconstruction for which machine learning (ML) shows state-of-the-art performance. Nowadays, we can build ML tools for such applications with real-world accuracy. However, each tool works well within the domain in which it has been trained and developed. Often, when we train a model on a dataset in one specific domain and test on another unseen domain known as an out of distribution (OOD) dataset, models or ML tools show a decrease in performance. For instance, when we train a simple classifier on real-world images and apply that model on the same classes but with a different domain like cartoons, paintings or sketches then the performance of ML tools disappoints. This presents serious challenges of domain generalisation (DG), domain adaptation (DA), and domain shifting. To enhance the power of ML tools, we can rebuild and retrain models from scratch or we can perform transfer learning. In this paper, we present a comparison study between vision-based technologies for domain-specific and domain-generalised methods. In this research we highlight that simple convolutional neural network (CNN) based deep learning methods perform poorly when they have to tackle domain shifting. Experiments are conducted on two popular vision-based benchmarks, PACS and Office-Home. We introduce an implementation pipeline for domain generalisation methods and conventional deep learning models. The outcome confirms that CNN-based deep learning models show poor generalisation compare to other extensive methods.