Catalogue Search | MBRL
Are you sure you want to remove the book from the shelf?
{{itemTitle}}
39,959
result(s) for
"State (computer science)"
Sort by:
The character of consent : the history of cookies and the future of technology policy
\"A timely history of digital consent told through the mundane yet highly contested web cookie: confronting cookies is an everyday experience for weary internet travelers, who click through and dodge cookie notifications each day. As part of an \"arrangement\" wherein services are exchanged for data, the use of cookies has been justified by notification practices like privacy policies and terms of service, and individuals \"agree\" to the arrangement by continuing on the site or clicking a box - thereby \"consenting\" to invasive data collection, analysis, and sharing\"-- Provided by publisher.
BOOK
Reward Machines: Exploiting Reward Function Structure in Reinforcement Learning
Reinforcement learning (RL) methods usually treat reward functions as black boxes. As such, these methods must extensively interact with the environment in order to discover rewards and optimal policies. In most RL applications, however, users have to program the reward function and, hence, there is the opportunity to make the reward function visible – to show the reward function’s code to the RL agent so it can exploit the function’s internal structure to learn optimal policies in a more sample efficient manner. In this paper, we show how to accomplish this idea in two steps. First, we propose reward machines, a type of finite state machine that supports the specification of reward functions while exposing reward function structure. We then describe different methodologies to exploit this structure to support learning, including automated reward shaping, task decomposition, and counterfactual reasoning with off-policy learning. Experiments on tabular and continuous domains, across different tasks and RL agents, show the benefits of exploiting reward structure with respect to sample efficiency and the quality of resultant policies. Finally, by virtue of being a form of finite state machine, reward machines have the expressive power of a regular language and as such support loops, sequences and conditionals, as well as the expression of temporally extended properties typical of linear temporal logic and non-Markovian reward specification.
Journal Article
Progress and prospects of the human–robot collaboration
Recent technological advances in hardware design of the robotic platforms enabled the implementation of various control modalities for improved interactions with humans and unstructured environments. An important application area for the integration of robots with such advanced interaction capabilities is human–robot collaboration. This aspect represents high socio-economic impacts and maintains the sense of purpose of the involved people, as the robots do not completely replace the humans from the work process. The research community’s recent surge of interest in this area has been devoted to the implementation of various methodologies to achieve intuitive and seamless human–robot-environment interactions by incorporating the collaborative partners’ superior capabilities, e.g. human’s cognitive and robot’s physical power generation capacity. In fact, the main purpose of this paper is to review the state-of-the-art on intermediate human–robot interfaces (bi-directional), robot control modalities, system stability, benchmarking and relevant use cases, and to extend views on the required future developments in the realm of human–robot collaboration.
Journal Article
New media futures : the rise of women in the digital arts
\"This project captures the spirit and contributions of women working in digital arts media and education in the Midwest--a region that, beginning in the mid-1980s, established itself as a center for the technological revolution. Bringing together historical research and interviews with key participants in the development of digital arts, this volume explores seminal events at the University of Illinois and the School of the Art Institute in Chicago that led to the establishment of interdisciplinary Renaissance Teams in advanced academic computing communities, which created a bridge to the humanities and to Chicago's emerging art scene. Digital games, virtual reality, supercomputing graphics, and internet, browser-based art all evolved during this revolution, underscored by the region's history of widespread social change and artistic innovation, and women artists and computing experts were integral to the development of these new media. Spurred by a dynamic of social feminist change, these events fostered an atmosphere of creative expression, innovation, interdisciplinary collaboration, while crossing gender lines and incorporating an artistic approach in a scientific environment. Ultimately, these events ushered in the digital age and paved the way for social media, which was both a product and a result of the confluence of the social relationships and human relationships nurtured by digital arts exploration in the region\"-- Provided by publisher.
Book
A Survey on the Explainability of Supervised Machine Learning
Predictions obtained by, e.g., artificial neural networks have a high accuracy but humans often perceive the models as black boxes. Insights about the decision making are mostly opaque for humans. Particularly understanding the decision making in highly sensitive areas such as healthcare or finance, is of paramount importance. The decision-making behind the black boxes requires it to be more transparent, accountable, and understandable for humans. This survey paper provides essential definitions, an overview of the different principles and methodologies of explainable Supervised Machine Learning (SML). We conduct a state-of-the-art survey that reviews past and recent explainable SML approaches and classifies them according to the introduced definitions. Finally, we illustrate principles by means of an explanatory case study and discuss important future directions.
Journal Article
Self-supervised learning methods and applications in medical imaging analysis: a survey
The scarcity of high-quality annotated medical imaging datasets is a major problem that collides with machine learning applications in the field of medical imaging analysis and impedes its advancement. Self-supervised learning is a recent training paradigm that enables learning robust representations without the need for human annotation which can be considered an effective solution for the scarcity of annotated medical data. This article reviews the state-of-the-art research directions in self-supervised learning approaches for image data with a concentration on their applications in the field of medical imaging analysis. The article covers a set of the most recent self-supervised learning methods from the computer vision field as they are applicable to the medical imaging analysis and categorize them as predictive, generative, and contrastive approaches. Moreover, the article covers 40 of the most recent research papers in the field of self-supervised learning in medical imaging analysis aiming at shedding the light on the recent innovation in the field. Finally, the article concludes with possible future research directions in the field.
Journal Article
Semantic Understanding of Scenes Through the ADE20K Dataset
Semantic understanding of visual scenes is one of the holy grails of computer vision. Despite efforts of the community in data collection, there are still few image datasets covering a wide range of scenes and object categories with pixel-wise annotations for scene understanding. In this work, we present a densely annotated dataset ADE20K, which spans diverse annotations of scenes, objects, parts of objects, and in some cases even parts of parts. Totally there are 25k images of the complex everyday scenes containing a variety of objects in their natural spatial context. On average there are 19.5 instances and 10.5 object classes per image. Based on ADE20K, we construct benchmarks for scene parsing and instance segmentation. We provide baseline performances on both of the benchmarks and re-implement state-of-the-art models for open source. We further evaluate the effect of synchronized batch normalization and find that a reasonably large batch size is crucial for the semantic segmentation performance. We show that the networks trained on ADE20K are able to segment a wide variety of scenes and objects.
Journal Article
Visualization in virtual reality: a systematic review
Rapidly growing virtual reality (VR) technologies and techniques have gained importance over the past few years, and academics and practitioners have been searching for efficient visualizations in VR. To date, the emphasis has been on the employment of game technologies. Despite the growing interest and potential, visualization studies have lacked a common baseline in the transition period of 2D visualizations to immersive ones. To this end, the presented study aims to provide a systematic literature review that explains the state-of-the-art research and future trends in visualization in virtual reality. The research framework is grounded in empirical and theoretical works of visualization. We characterize the reviewed literature based on three dimensions: (a) Connection with visualization background and theory, (b) Evaluation and design considerations for virtual reality visualization, and (c) Empirical studies. The results from this systematic review suggest that: (1) There are only a few studies that focus on creating standard guidelines for virtual reality, and each study individually provides a framework or employs previous studies on traditional 2D visualizations; (2) With the myriad of advantages provided for visualization and virtual reality, most of the studies prefer to use game engines; (3) Although game engines are extensively used, they are not convenient for critical scientific studies; and (4) 3D versions of traditional statistical visualization techniques, such as bar plots and scatter plots, are still commonly used in the data visualization context. This systematic review attempts to add a clear picture of the emerging contexts, different elements, and interdependencies to the literature.
Journal Article
Image based fruit category classification by 13-layer deep convolutional neural network and data augmentation
Fruit category identification is important in factories, supermarkets, and other fields. Current computer vision systems used handcrafted features, and did not get good results. In this study, our team designed a 13-layer convolutional neural network (CNN). Three types of data augmentation method was used: image rotation, Gamma correction, and noise injection. We also compared max pooling with average pooling. The stochastic gradient descent with momentum was used to train the CNN with minibatch size of 128. The overall accuracy of our method is 94.94%, at least 5 percentage points higher than state-of-the-art approaches. We validated this 13-layer is the optimal structure. The GPU can achieve a 177× acceleration on training data, and a 175× acceleration on test data. We observed using data augmentation can increase the overall accuracy. Our method is effective in image-based fruit classification.
Journal Article