This paper proposes a novel deep reinforcement learning architecture that was inspired by previous tree structured architectures which were only useable in discrete action spaces. Policy Prediction Network offers a way to improve sample complexity and performance on continuous control problems in exchange for extra computation at training time but at no cost in computation at rollout time. Our approach integrates a mix between model-free and model-based reinforcement learning. Policy Prediction Network is the first to introduce implicit model-based learning to Policy Gradient algorithms for continuous action space and is made possible via the empirically justified clipping scheme. Our experiments are focused on the MuJoCo environments so that they can be compared with similar work done in this area.

We present a new explainable AI (XAI) framework aimed at increasing justified human trust and reliance in the AI machine through explanations. We pose explanation as an iterative communication process, i.e. dialog, between the machine and human user. More concretely, the machine generates sequence of explanations in a dialog which takes into account three important aspects at each dialog turn: (a) human's intention (or curiosity); (b) human's understanding of the machine; and (c) machine's understanding of the human user. To do this, we use Theory of Mind (ToM) which helps us in explicitly modeling human's intention, machine's mind as inferred by the human as well as human's mind as inferred by the machine. In other words, these explicit mental representations in ToM are incorporated to learn an optimal explanation policy that takes into account human's perception and beliefs. Furthermore, we also show that ToM facilitates in quantitatively measuring justified human trust in the machine by comparing all the three mental representations. We applied our framework to three visual recognition tasks, namely, image classification, action recognition, and human body pose estimation. We argue that our ToM based explanations are practical and more natural for both expert and non-expert users to understand the internal workings of complex machine learning models. To the best of our knowledge, this is the first work to derive explanations using ToM. Extensive human study experiments verify our hypotheses, showing that the proposed explanations significantly outperform the state-of-the-art XAI methods in terms of all the standard quantitative and qualitative XAI evaluation metrics including human trust, reliance, and explanation satisfaction.

In the EU-funded MuMMER project, we have developed a social robot designed to interact naturally and flexibly with users in public spaces such as a shopping mall. We present the latest version of the robot system developed during the project. This system encompasses audio-visual sensing, social signal processing, conversational interaction, perspective taking, geometric reasoning, and motion planning. It successfully combines all these components in an overarching framework using the Robot Operating System (ROS) and has been deployed to a shopping mall in Finland interacting with customers. In this paper, we describe the system components, their interplay, and the resulting robot behaviours and scenarios provided at the shopping mall.

Federated Imitation Learning: A Privacy Considered Imitation Learning Framework for Cloud Robotic Systems with Heterogeneous Sensor Data Boyi Liu 1,4, Lujia Wang 1, Ming Liu 2 and Cheng-Zhong Xu 3 Abstract -- Humans are capable of learning a new behavior by observing others perform the skill. Similarly, robots can also implement this by imitation learning. Furthermore, if with external guidance, humans can master the new behavior more efficiently. So how can robots achieve this? T o address the issue, we present Federated Imitation Learning (FIL) in the paper . Firstly, a knowledge fusion algorithm is proposed for the cloud fusing knowledge from local robots. Then, a knowledge transfer scheme is presented to facilitate local robots acquiring knowledge from the cloud. With FIL, a robot is capable of utilizing knowledge from other robots to increase its imitation learning in accuracy and training efficiency. FIL considers information privacy and data heterogeneity when robots share knowledge. It is suitable to be deployed in cloud robotic systems. Finally, we conduct experiments of a simplified self-driving task for robots (cars). The experimental results demonstrate that FIL increases imitation learning efficiency and accuracy of local robots in cloud robotic systems. I. INTRODUCTION In tradition imitation learning scenarios, demonstrations provide a descriptive medium for specifying robotic tasks. Prior work has shown that robots can acquire a range of complex skills through demonstration, such as table tennis [1], drawer opening [2], and multistage manipulation tasks [3]. Nevertheless, there exists a number of problems in the application of imitation learning.

The ability of the computer program to imitate the human intelligence needed for the task is termed as artificial intelligence (AI). Integration of the artificial intelligence in education sector creates revolution through its result driven approach. The applications in solving the issues such as language processing, reasoning, planning, and cognitive modeling increases the demand for the AI in the education sector. In another learning approach, AI can help organize and synthesize content to support content delivery. The Research Insights has added a new report to its source.

GE Healthcare announced the Food and Drug Administration's 510(k) clearance of Critical Care Suite, a collection of artificial intelligence (AI) algorithms embedded on a mobile X-ray device. Built-in collaboration with UC San Francisco (UCSF), using GE Healthcare's Edison platform, the AI algorithms help to reduce the turn-around time it can take for radiologists to review a suspected pneumothorax, a type of collapsed lung. Additional partners in the development of Critical Care Suite include St. Luke's University Health Network, Humber River Hospital, and CARING – Mahajan Imaging – India. A prioritized "STAT" X-ray can sit waiting for up to eight hours for a radiologist's review1. However, when a patient is scanned on a device with Critical Care Suite, the system automatically analyzes the images by simultaneously searching for a pneumothorax.

Quest Diagnostics, a provider of diagnostic information services, and hc1, the bioinformatics leader in precision testing has unveiled Quest Lab Stewardship powered by hc1, an innovative new service that employs machine learning to harmonize laboratory testing across health systems in order to help optimize laboratory test utilization. Healthcare system wastes around $765 billion a year, due to factors such as unnecessary or inefficiently delivered services as well as missed prevention opportunities, according to the National Academy of Medicine. Although laboratory testing reflects only about 2-3% of overall health care costs in the United States, ordering lab tests is healthcare's single highest-volume activity.[ii] Under-and overutilization* of lab tests can adversely affect clinical decisions, such as by prompting unnecessary or delayed procedures to address missed diagnoses. Quest Lab Stewardship is the result of a strategic collaboration between Quest and hc1 focused on improving costs and clinical impact of lab testing, in- and out- of hospital settings.

A deep learning convolutional neural network model is used to explore the possibilities of estimating tropical cyclone (TC) intensity from satellite images in the 37- and 85–92-GHz bands. The model, called "DeepMicroNet," has unique properties such as a probabilistic output, the ability to operate from partial scans, and resiliency to imprecise TC center fixes. The 85–92-GHz band is the more influential data source in the model, with 37 GHz adding a marginal benefit. Training the model on global best track intensities produces model estimates precise enough to replicate known best track intensity biases when compared to aircraft reconnaissance observations. Model root-mean-square error (RMSE) is 14.3 kt (1 kt 0.5144 m s 1) compared to two years of independent best track records, but this improves to an RMSE of 10.6 kt when compared to the higher-standard aircraft reconnaissance-aided best track dataset, and to 9.6 kt compared to the reconnaissance-aided best track when using the higher-resolution TRMM TMI and Aqua AMSR-E microwave observations only. A shortage of training and independent testing data for category 5 TCs leaves the results at this intensity range inconclusive. Based on this initial study, the application of deep learning to TC intensity analysis holds tremendous promise for further development with more advanced methodologies and expanded training datasets. If you would like to learn more about this work check out the publication titled, "Using Deep Learning to Estimate Tropical Cyclone Intensity from Satellite Passive Microwave Imagery". If you would like to learn more about models for predicting tropical storms, checkout this presentation by NASA titled, "Tropical Cyclone Intensity Estimation Using Deep Convolutional Neural Networks".

Artificial intelligence and machine learning may be ideal for picking up the day-to-day tasks of running enterprises, but still fall flat when it comes to innovation or reacting to unforeseen or one-off events. While enterprise-grade AI is still a ways off, it's incumbent on business and IT leaders to start piloting and exploring the advantages AI potentially offers. That's the word coming out of a recent report from the MIT Task Force on the Work of the Future, which looked at AI as part of a broad range of changes sweeping the employment scene and workplace. "We are a long way from AI systems that can read the news, re-plan supply chains in response to anticipated events like Brexit or trade disputes, and adapt production tasks to new sources of parts and materials," state the report's authors, David Autor of the National Bureau of Economic Research, along with David Mindell and Elisabeth Reynolds, both with MIT. For starters, data – the fuel that propels AI decision-making – is not ready for the leap.

Artificial intelligence and machine learning may be ideal for picking up the day-to-day tasks of running enterprises, but still fall flat when it comes to innovation or reacting to unforeseen or one-off events. While enterprise-grade AI is still a ways off, it's incumbent on business and IT leaders to start piloting and exploring the advantages AI potentially offers. That's the word coming out of a recent report from the MIT Task Force on the Work of the Future, which looked at AI as part of a broad range of changes sweeping the employment scene and workplace. "We are a long way from AI systems that can read the news, re-plan supply chains in response to anticipated events like Brexit or trade disputes, and adapt production tasks to new sources of parts and materials," state the report's authors, David Autor of the National Bureau of Economic Research, along with David Mindell and Elisabeth Reynolds, both with MIT. For starters, data – the fuel that propels AI decision-making – is not ready for the leap.