Auflistung nach:
Auflistung Künstliche Intelligenz 29(4) - November 2015 nach Titel
1 - 10 von 16
Treffer pro Seite
Sortieroptionen
- ZeitschriftenartikelAccounting for Task-Difficulty in Active Multi-Task Robot Control Learning(KI - Künstliche Intelligenz: Vol. 29, No. 4, 2015) Fabisch, Alexander; Metzen, Jan Hendrik; Krell, Mario Michael; Kirchner, FrankContextual policy search is a reinforcement learning approach for multi-task learning in the context of robot control learning. It can be used to learn versatilely applicable skills that generalize over a range of tasks specified by a context vector. In this work, we combine contextual policy search with ideas from active learning for selecting the task in which the next trial will be performed. Moreover, we use active training set selection for reducing detrimental effects of exploration in the sampling policy. A core challenge in this approach is that the distribution of the obtained rewards may not be directly comparable between different tasks. We propose the novel approach PUBSVE for estimating a reward baseline and investigate empirically on benchmark problems and simulated robotic tasks to which extent this method can remedy the issue of non-comparable reward.
- ZeitschriftenartikelAutonomous Learning of Representations(KI - Künstliche Intelligenz: Vol. 29, No. 4, 2015) Walter, Oliver; Haeb-Umbach, Reinhold; Mokbel, Bassam; Paassen, Benjamin; Hammer, BarbaraBesides the core learning algorithm itself, one major question in machine learning is how to best encode given training data such that the learning technology can efficiently learn based thereon and generalize to novel data. While classical approaches often rely on a hand coded data representation, the topic of autonomous representation or feature learning plays a major role in modern learning architectures. The goal of this contribution is to give an overview about different principles of autonomous feature learning, and to exemplify two principles based on two recent examples: autonomous metric learning for sequences, and autonomous learning of a deep representation for spoken language, respectively.
- ZeitschriftenartikelAutonomous Learning of State Representations for Control: An Emerging Field Aims to Autonomously Learn State Representations for Reinforcement Learning Agents from Their Real-World Sensor Observations(KI - Künstliche Intelligenz: Vol. 29, No. 4, 2015) Böhmer, Wendelin; Springenberg, Jost Tobias; Boedecker, Joschka; Riedmiller, Martin; Obermayer, KlausThis article reviews an emerging field that aims for autonomous reinforcement learning (RL) directly on sensor-observations. Straightforward end-to-end RL has recently shown remarkable success, but relies on large amounts of samples. As this is not feasible in robotics, we review two approaches to learn intermediate state representations from previous experiences: deep auto-encoders and slow-feature analysis. We analyze theoretical properties of the representations and point to potential improvements.
- ZeitschriftenartikelBeyond Manual Tuning of Hyperparameters(KI - Künstliche Intelligenz: Vol. 29, No. 4, 2015) Hutter, Frank; Lücke, Jörg; Schmidt-Thieme, LarsThe success of hand-crafted machine learning systems in many applications raises the question of making machine learning algorithms more autonomous, i.e., to reduce the requirement of expert input to a minimum. We discuss two strategies towards this goal: (1) automated optimization of hyperparameters (including mechanisms for feature selection, preprocessing, model selection, etc) and (2) the development of algorithms with reduced sets of hyperparameters. Since many research directions (e.g., deep learning), show a tendency towards increasingly complex algorithms with more and more hyperparamters, the demand for both of these strategies continuously increases. We review recent hyperparameter optimization methods and discuss data-driven approaches to avoid the introduction of hyperparameters using unsupervised learning. We end in discussing how these complementary strategies can work hand-in-hand, representing a very promising approach towards autonomous machine learning.
- ZeitschriftenartikelConsumers’ Perception of Augmented Reality as an Emerging end User Technology: Social Media Monitoring Applied(KI - Künstliche Intelligenz: Vol. 29, No. 4, 2015) Stockinger, HannaAugmented reality (AR) is at a point where it is mature enough to be used in publicly available consumer applications. Nevertheless, the real commercial breakthrough of AR is still lacking. One reason for this is a deficit in consumer research regarding users’ perception, acceptance and attitude towards this technology. This paper remedies this lack by means of a novel social media monitoring method. Thereby, the population of 48,560 consumer comments published up until July 2013 on English speaking online community websites treating the topic AR, were extracted from the web and analyzed. The results indicate that consumers evaluate the technology positively and highly appreciate its idea and concept. Still, some obstacles need to be overcome before AR succeeds in becoming adopted by the mainstream user. Above all, there is a lack of consumer awareness, particularly regarding specific applications or products, in addition to technical, developmental and ethical problems. Nevertheless, AR technologies are on the rise and will become more important in the end user sphere, especially in the gaming sector and for information and knowledge transfer.
- ZeitschriftenartikelGeometric Design Principles for Brains of Embodied Agents(KI - Künstliche Intelligenz: Vol. 29, No. 4, 2015) Ay, NihatI propose a formal model of the sensorimotor loop and discuss corresponding extrinsic embodiment constraints and the intrinsic degrees of freedom. These degrees constitute the basis for adaptation in terms of learning and should therefore be coupled with the embodiment constraints. Notions of sufficiency and embodied universal approximation allow us to formulate principles for such a coupling. This provides a geometric approach to the design of control architectures for embodied agents.
- ZeitschriftenartikelInterview with Werner von Seelen(KI - Künstliche Intelligenz: Vol. 29, No. 4, 2015) Paaßen, Benjamin
- ZeitschriftenartikelLearning Feedback in Intelligent Tutoring Systems(KI - Künstliche Intelligenz: Vol. 29, No. 4, 2015) Gross, Sebastian; Mokbel, Bassam; Hammer, Barbara; Pinkwart, NielsIntelligent Tutoring Systems (ITSs) are adaptive learning systems that aim to support learners by providing one-on-one individualized instruction. Typically, instructing learners in ITSs is build on formalized domain knowledge and, thus, the applicability is restricted to well-defined domains where knowledge about the domain being taught can be explicitly modeled. For ill-defined domains, human tutors still by far outperform the performance of ITSs, or the latter are not applicable at all. As part of the DFG priority programme “Autonomous Learning”, the FIT project has been conducted over a period of 3 years pursuing the goal to develop novel ITS methods, that are also applicable for ill-defined problems, based on implicit domain knowledge extracted from educational data sets. Here, machine learning techniques have been used to autonomously infer structures from given learning data (e.g., student solutions) and, based on these structures, to develop strategies for instructing learners.
- ZeitschriftenartikelNews(KI - Künstliche Intelligenz: Vol. 29, No. 4, 2015)
- ZeitschriftenartikelOnline Learning of Bipedal Walking Stabilization(KI - Künstliche Intelligenz: Vol. 29, No. 4, 2015) Missura, Marcell; Behnke, SvenBipedal walking is a complex whole-body motion with inherently unstable dynamics that makes the design of a robust controller particularly challenging. While a walk controller could potentially be learned with the hardware in the loop, the destructive nature of exploratory motions and the impracticality of a high number of required repetitions render most of the existing machine learning methods unsuitable for an online learning setting with real hardware. In a project in the DFG Priority Programme Autonomous Learning, we are investigating ways of bootstrapping the learning process with basic walking skills and enabling a humanoid robot to autonomously learn how to control its balance during walking.