During the architectural analysis, abstract artifacts need to be precisely identified and specified in order to efficiently guide the development, evolution and deployment of the overall system. Considering such an early stage, architectural decisions become even more challenging due to the lack of knowledge about the system but, at the same time, they are crucial to fulfill the many quality criteria imposed [12]. Artificial intelligence techniques and, more specifically, metaheuristics, can support software engineers in their decision processes by providing them with effective methods to explore a great deal of software designs, each one determined by a different trade-off among the required quality aspects. Such a scenario can be viewed as one of the goals of the search-based software engineering (SBSE) field[14], in which optimization techniques are applied to the resolution of software engineering (SE) tasks conveniently reformulated as search problems. However, solving human-centered activities in a fully automated way seems to be unrealistic, especially for those related to the analysis phase. Certainly, trying to capture the richness of human knowledge only by means of software metrics still represents an unresolved matter to the SE community [32]. Hence, most of the evaluation methods proposed at the architectural level strongly rely on the expert's judgment [10], making extremely difficult to precisely formulate a quantitative fitness function. Given the relevance of the software architect for the design process, searchbased approaches should benefit from his/her knowledge and expertise in order to address the optimization problem in the same way s/he would do it. Interactive optimization [21] constitutes a compelling paradigm here.

AI alignment is about ensuring AI systems only pursue goals and activities that are beneficial to humans. Most of the current approach to AI alignment is to learn what humans value from their behavioural data. This paper proposes a different way of looking at the notion of alignment, namely by introducing AI Alignment Dialogues: dialogues with which users and agents try to achieve and maintain alignment via interaction. We argue that alignment dialogues have a number of advantages in comparison to data-driven approaches, especially for behaviour support agents, which aim to support users in achieving their desired future behaviours rather than their current behaviours. The advantages of alignment dialogues include allowing the users to directly convey higher-level concepts to the agent, and making the agent more transparent and trustworthy. In this paper we outline the concept and high-level structure of alignment dialogues. Moreover, we conducted a qualitative focus group user study from which we developed a model that describes how alignment dialogues affect users, and created design suggestions for AI alignment dialogues. Through this we establish foundations for AI alignment dialogues and shed light on what requires further development and research.

He graduated w/Special Honors in ChE & later Cert. in Quality Mgmt. Syndicated research (silicon photonics); writes for trade press and web communities. Served Fortune 1000 and FTSE 250 companies in a variety of projects, including global market/product strategy and most recently deep analytics and forecasting. Following ten years in government research and management (Deputy Director, National Measurement Laboratory (US DoC NIST) and Chief, Chemical Engineering Division of NIST), Mr. Bateman worked at several start-ups in electronics and antennas, resulting in 100s of products and several patents. Mr. Bateman led efforts to bring design and manufacturing of telematics and in-building antennas to China and Malaysia, and was key in creating an Automotive Connectivity Unit in Laird, and led technical diligence for multiple acquisitions and creation of an Infrastructure Antenna Unit.

Summary: A new computer interface allowed participants to convey their emotions through music by changing elements of the musical tune. New research conducted by experts from Durham University's Department of Music found that people are able to convey particular emotions through music by changing certain elements of the musical tune. The researchers created an interactive computer interface called EmoteControl which allows users to control six cues (tempo, pitch, articulation, dynamics, brightness, and mode) of a musical piece in real-time. The participants were asked to show how they think seven different emotions (sadness, calmness, joy, anger, fear, power, and surprise) should sound as music. They did this by changing the musical cues in EmoteControl, essentially allowing them to create their own variations of a range of music pieces that portrayed different emotions.

When explaining the decisions of deep neural networks, simple stories are tempting but dangerous. Especially in computer vision, the most popular explanation approaches give a false sense of comprehension to its users and provide an overly simplistic picture. We introduce an interactive framework to understand the highly complex decision boundaries of modern vision models. It allows the user to exhaustively inspect, probe, and test a network's decisions. Across a range of case studies, we compare the power of our interactive approach to static explanation methods, showing how these can lead a user astray, with potentially severe consequences.

Andrew Bird is the data and analytics manager for Vesparum Capital. He leads the software and data science teams at Vesparum, overseeing full stack web development in Django / React. He is an Australian actuary (FIAA, CERA), who has previously worked with Deloitte Consulting in financial services. Andrew also currently works as a full-stack developer for Draftable Pvt. Ltd. He manages ongoing development of the donation portal for Effective Altruism Australia website, on a voluntary basis.

The ability to specify a task without having to write special software is an important and prominent feature for a mobile service robot deployed in a crowded office environment, working around and interacting with people. In this paper, we contribute an interactive approach for enabling the users to teach tasks to a mobile service robot through verbal commands. The input is given as typed or spoken instructions, which are then mapped to the available sensing and actuation primitives on the robot. The main contributions of this work are the addition of conditionals on sensory information that the specified actions to be executed in a closed-loop manner, and a correction mode that allows an existing task to be modified or corrected at a later time by providing a replacement action during the test execution. We describe all the components of the system along with the implementation details and illustrative examples in depth. We also discuss the extensibility of the presented system, and point out potential future extensions.