Explainable artificial intelligence (XAI) aims at addressing complex problems by coupling solutions with reasons that justify the provided answer. In the context of Answer Set programming (ASP) the user may be interes...
详细信息
the proceedings contain 6 papers. the topics discussed include: the promise and perils of using machine learning when engineering software;neural language models for code quality identification;are machine programming...
ISBN:
(纸本)9781450394567
the proceedings contain 6 papers. the topics discussed include: the promise and perils of using machine learning when engineering software;neural language models for code quality identification;are machine programming systems using right source-code measures to select code repositories?;on the application of machine learning models to assess and predict software reusability;using machine learning to guide the application of software refactorings: a preliminary exploration;and DeepCrash: deep metric learning for crash bucketing based on stack trace.
Two main approaches in the theory and practice of teaching are used to acquire knowledge: inductive and deductive. the focus of the report is on how to use both approaches effectively in the process of teaching studen...
详细信息
Technology can be empowering: It can lift the burden from tasks we find dreadful and help us excel in tasks we enjoy. Equally, a mismatch between the user interface (UI) and our skills can make us feel incompetent and...
详细信息
ISBN:
(纸本)9781665404921
Technology can be empowering: It can lift the burden from tasks we find dreadful and help us excel in tasks we enjoy. Equally, a mismatch between the user interface (UI) and our skills can make us feel incompetent and reluctant towards the technology. Withthe trend to increase the level of automation in fields beyond traditional manufacturing, such as laboratories or small workshops, new technologies such as collaborative robots (cobots) are entering the workplace. the technology literacy levels of professionals in these fields may vary greatly depending on their age, gender, education and personal interests, creating a challenge in designing universal cobot Uts. In this qualitative study, we address the question of how introducing interaction skills and intelligence to cobots may inhibit or encourage users to use them in their work context. the interviews, performed with 15 individuals working in laboratory settings, gave rise to numerous themes relevant to the design of user-empowering cobot interfaces for individuals with varying technology literacy levels: As "programming may not be for a normal person", talking to a robot may not be for another. Incorporating the unique interests, fears, personal and domain experience of the end users can contribute to the design and development of cobot interfacesas diverse as their needs, thus maximizing the likelihood of successful integration across diverse work environments.
this paper presents the rationale and design of the trust plane for ImPACT, a federated platform for managed sharing of restricted data. Key elements of the architecture include Web-based notaries for credential estab...
详细信息
ISBN:
(纸本)9780738113302
this paper presents the rationale and design of the trust plane for ImPACT, a federated platform for managed sharing of restricted data. Key elements of the architecture include Web-based notaries for credential establishment based on declarative templates for Data Usage Agreements, a federated authorization pipeline, integration of popular services for identity management, and programmable policy based on a logical trust model with a repository of linked certificates. We show how these elements of the trust plane work in concert, and set the ideas in context with principles of federated authorization. A focus and contribution of the paper is to explore limitations of the resulting architecture and tensions among competing design goals. We also point the way toward future extensions, including policy-checked data access from cloud-hosted data enclaves with enhanced defenses against data leakage and exfiltration.
End-to-end (E2E) Spoken Language Understanding (SLU) systems infer structured information directly from the speech signal using a single model. Due to the success of virtual assistants and the increasing demand for sp...
详细信息
this paper presents a novel paradigm, based on carry-look-ahead principles, for finding the negation of a high-precision binary integer represented in two’s complement, and also for converting a two’s complement num...
this paper presents a novel paradigm, based on carry-look-ahead principles, for finding the negation of a high-precision binary integer represented in two’s complement, and also for converting a two’s complement number to sign-and-magnitude (i.e., absolute value), and vice versa. theoretical analysis of the proposed algorithm yields a logarithmic bound on delay with increasing input size n. Implementation results of the proposed hardware show linear growth in complexity. the linear growth for lookup tables is also small: around 1.1n for the hardware alone and less than 2n for the hardware with a serial transceiver after n=512, due to overhead. Flip-flop usage grows similarly. the proposed hardware has a delay of 2.254 ns or less for all three aforementioned operations.
In this work, we address a task allocation problem for human multi-robot settings. Given a set of tasks to perform, we formulate a general Mixed-Integer Linear programming (MILP) problem aiming at minimizing the overa...
详细信息
ISBN:
(纸本)9781665404921
In this work, we address a task allocation problem for human multi-robot settings. Given a set of tasks to perform, we formulate a general Mixed-Integer Linear programming (MILP) problem aiming at minimizing the overall execution time while optimizing the quality of the executed tasks as well as human and robotic workload. Different skills of the agents, both human and robotic, are taken into account and human operators are enabled to either directly execute tasks or play supervisory roles;moreover, multiple manipulators can tightly collaborate if required to carry out a task. Finally, as realistic in human contexts, human parameters are assumed to vary over time, e.g., due to increasing human level of fatigue. therefore, online monitoring is required and re-allocation is performed if needed. Simulations in a realistic scenario with two manipulators and a human operator performing an assembly task validate the effectiveness of the approach.
Our work in this paper concerns a wireless sensor network (WSN) problem, called the path exposure with communication range uncertainty (EXPO-RU) problem. Nodes in the network are assumed to rely on energy harvesting f...
详细信息
ISBN:
(纸本)9780738113302
Our work in this paper concerns a wireless sensor network (WSN) problem, called the path exposure with communication range uncertainty (EXPO-RU) problem. Nodes in the network are assumed to rely on energy harvesting from the ambient environment to achieve prolonged operation of a WSN deployed to monitor unauthorized traversal along a given path. Fluctuations in the harvested energy are assumed to affect each node's transmission range. A 3-state probabilistic model where each node can be either in a full, reduced, or depleted energy state is used. We present two algorithms that complement existing algorithms in the literature to assess the reliability of a given energy harvesting wireless sensor network (EH-WSN). Each algorithm provides a basic tool that enables the construction of many other algorithms to bound the exact solution of the problem. We also present numerical results that show the impact of using the presented algorithms.
Learning Management System (LMS) plays an essential role in interactive learning, especially after the COVID-19 outbreak with a rapid shift from traditional classroom learning to online learning. LMS also facilitates ...
详细信息
ISBN:
(数字)9798350356694
ISBN:
(纸本)9798350356700
Learning Management System (LMS) plays an essential role in interactive learning, especially after the COVID-19 outbreak with a rapid shift from traditional classroom learning to online learning. LMS also facilitates the continuous collection and evaluation of students' performance. In this paper, we focus on predicting students' in-class performance (i.e., in-lab) from their homework performance (i.e., pre-lab) using the data collected from LMS with four experimental exercises for the programming techniques course. We also investigate several machine learning methods and hyperparameters for model selection. the results show that Random Forest has the best performance. this investigated cause-effect relationship between pre- and in-lab grades not only helps teachers with a better understanding of the curriculum but also students withtheir learning results.
暂无评论