--While interacting with another person, our reactions and behavior are much affected by the emotional changes within the temporal context of the interaction. Our intrinsic affective appraisal comprising perception, self-assessment, and the affective memories with similar social experiences will drive specific, and in most cases addressed as proper, reactions within the interaction. This paper proposes the roadmap for the development of multimodal research which aims to empower a robot with the capability to provide proper social responses in a Human-Robot Interaction (HRI) scenario. Our capabilities of both perceiving and reacting to the affective behavior of other persons are fine-tuned based on the observed social response of our interaction peers. We usually perceive how others are behaving towards us by reading their affective behavior through the processing of audio/visual cues [13].

With the increasing use of machine learning in practice and because of legal regulations like EU's GDPR, it becomes indispensable to be able to explain the prediction and behavior of machine learning models. An example of easy to understand explanations of AI models are counterfactual explanations. However, for many models it is still an open research problem how to efficiently compute counterfactual explanations. We investigate how to efficiently compute counterfactual explanations of learning vector quantization models. In particular, we propose different types of convex and non-convex programs depending on the used learning vector quantization model.

Manipulation tasks such as preparing a meal or assembling furniture remain highly challenging for robotics and vision. The supervised approach of imitation learning can handle short tasks but suffers from compounding errors and the need of many demonstrations for longer and more complex tasks. Reinforcement learning (RL) can find solutions beyond demonstrations but requires tedious and task-specific reward engineering for multi-step problems. In this work we address the difficulties of both methods and explore their combination. To this end, we propose a RL policies operating on pre-trained skills, that can learn composite manipulations using no intermediate rewards and no demonstrations of full tasks. We also propose an efficient training of basic skills from few synthetic demonstrated trajectories by exploring recent CNN architectures and data augmentation. We show successful learning of policies for composite manipulation tasks such as making a simple breakfast. Notably, our method achieves high success rates on a real robot, while using synthetic training data only.

Humans as designers have quite versatile problem-solving strategies. Computer agents on the other hand can access large scale computational resources to solve certain design problems. Hence, if agents can learn from human behavior, a synergetic human-agent problem solving team can be created. This paper presents an approach to extract human design strategies and implicit rules, purely from historical human data, and use that for design generation. A two-step framework that learns to imitate human design strategies from observation is proposed and implemented. This framework makes use of deep learning constructs to learn to generate designs without any explicit information about objective and performance metrics. The framework is designed to interact with the problem through a visual interface as humans did when solving the problem. It is trained to imitate a set of human designers by observing their design state sequences without inducing problem-specific modelling bias or extra information about the problem. Furthermore, an end-to-end agent is developed that uses this deep learning framework as its core in conjunction with image processing to map pixel-to-design moves as a mechanism to generate designs. Finally, the designs generated by a computational team of these agents are then compared to actual human data for teams solving a truss design problem. Results demonstrates that these agents are able to create feasible and efficient truss designs without guidance, showing that this methodology allows agents to learn effective design strategies.

These are the things our readers went nuts for last month. If you make a purchase by clicking one of our links, we may earn a small share of the revenue. However, our picks and opinions are independent from USA TODAY's newsroom and any business incentives. When the dog days of summer arrive and the temperature rises, prices across a ton of retailers tend to drop. There's also Prime Day of course, one of the biggest shopping holidays of the year, when Amazon slashes their prices across the board in an attempt to compete with Black Friday sales. Nordstrom happens to use a similar technique to get ahead of the end-of-summer sales curve with their massive Nordstrom Anniversary sale, which features discounts on a ton of fashion, beauty, and home products.

For years, the Sonos Wi-Fi speakers have been beloved by music fans for the ease of listening to streaming music at home with great sound. Also, add the ability to add multiple speakers for even better sound without having to resort to stringing speaker wire all over. The one drawback: Sonos speakers can be pricey, topping off at $499 per speaker and even higher for the $699 TV Playbar. So good news consumers: The most affordable way to get into the Sonos system goes on sale Thursday. But you won't find the speakers at Best Buy, Amazon or any of the other retailers which usually stock Sonos products.

In a recent conference in Tokyo, the innovation of a Machine Learning-Based Traffic Sign Recognition by cars has created a huge buzz. Deemed to be the most powerful innovation of the decade, this path-breaking technology has also found its use in autonomous cars of today. The concept came to life in 2009, in a paper that proposed the ideas of in-vehicle camera traffic sign recognition into practical uses so that the traffic system can benefit from it. Although the concept might still be nascent, the machine learning-based traffic sign recognition can add remarkably convenience to both self-driven and autonomous cars. One of the most significant breakthroughs in Machine Learning Applications, the most prominent feature of this innovative the system is the usage of cameras to detect, recognize and track road signs in real-time.

No industry is subject to waves of change as often as technology. It has a long reach, touching everything we use. So how do innovations, such as Machine Learning, AI and automation, affect the well-established technologies of Service Management? Because, as Zaid Ismail of AfroCentric Group explains, the two can no longer be separated. "Service management has become relevant across the enterprise, not just within IT." Research by IDC has recognized the need for continuous innovation. Traditional ITSM tools do not use the data and knowledge the Service Desk team records to help prioritize issues, which can negatively impact productivity and service levels if unresolved.

On this livestream from KubeCon CloudNativeCon China, we're sitting down with Alejandro Saucedo, Chief Scientist at the Institute for Ethical AI & Machine Learning and Dr. Han Xiao, Engineering Lead at Tencent AI Lab to learn more about how Kubernetes is used in an AI&ML context. When one is running complicated AI/ML workloads at scale, Kubernetes fits naturally as the solution due to its ability to scale rapidly, portability, and the variety of tools available for AI & ML use cases on Kubernetes, Kubeflow. Rather than setting out to recreate the wheel, Kubeflow offers those working with AI & ML data sets the best-of-the-best options for deploying AI/ML workloads on Kubernetes by bringing together Jupyter notebooks, TensorFlow model training to adjust CPU & GPU cluster size for workloads, TensorFlow serving containers to export trained models to Kubernetes, and Kubeflow Pipelines.

In 2017, DeepMind started trialling a new app with the Royal Free hospital in London. Called Streams, it was intended to help clinicians identify and monitor acute kidney injury (AKI) – a condition linked to 100,000 deaths in the UK every year. But unlike most of DeepMind's headline-grabbing work, Streams doesn't contain a jot of artificial intelligence. Instead, the app brings together medical information, such as blood test results and vital signs, and notifies clinicians when a patient's kidney health deteriorates, using a well-established formula for evaluating kidney function. Now DeepMind has provided the first hints that using artificial intelligence might be a much better way of assessing whether someone is at risk of AKI.