| 1. |
|
|
| 2. |
|
|
| 3. |
- Karlsson, Lars, et al.
(author)
-
To secure an anchor : a recovery planning approach to ambiguity in perceptual anchoring
- 2008
-
In: AI Communications. - Amsterdam : IOS Press. - 0921-7126 .- 1875-8452. ; 21:1, s. 1-14
-
Journal article (peer-reviewed)abstract
- An autonomous robot using symbolic reasoning, sensing and acting in a real environment needs the ability to create and maintain the connection between symbols representing objects in the world and the corresponding perceptual representations given by its sensors. This connection has been named perceptual anchoring. In complex environments, anchoring is not always easy to establish: the situation may often be ambiguous as to which percept actually corresponds to a given symbol. In this paper, we extend perceptual anchoring to deal robustly with ambiguous situations by providing general methods for detecting them and recovering from them. We consider different kinds of ambiguous situations. We also present methods to recover from these situations based onautomatically formulating them as conditional planning problems that then are solved by a planner. We illustrate our approach by showing experiments involving a mobile robot equipped with a color camera and an electronic nose.
|
|
| 4. |
- Klügl, Franziska, 1970-, et al.
(author)
-
Accelerating route choice learning with experience sharing in a commuting scenario : An agent-based approach
- 2021
-
In: AI Communications. - : IOS Press. - 0921-7126 .- 1875-8452. ; 34:1, s. 105-119
-
Journal article (peer-reviewed)abstract
- Navigation apps have become more and more popular, as they give information about the current traffic state to drivers who then adapt their route choice. In commuting scenarios, where people repeatedly travel between a particular origin and destination, people tend to learn and adapt to different situations. What if the experience gained from such a learning task is shared via an app? In this paper, we analyse the effects that adaptive driver agents cause on the overall network, when those agents share their aggregated experience about route choice in a reinforcement learning setup. In particular, in this investigation, Q-learning is used and drivers share what they have learnt about the system, not just information about their current travel times. Using a classical commuting scenario, we show that experience sharing can improve convergence times that underlie a typical learning task. Further, we analyse individual learning dynamics to get an impression how aggregate and individual dynamics are related to each other. Based on that interesting pattern of individual learning dynamics can be observed that would otherwise be hidden in an only aggregate analysis.
|
|
| 5. |
- Kovács, György, Postdoctoral researcher, 1984-, et al.
(author)
-
Leveraging external resources for offensive content detection in social media
- 2022
-
In: AI Communications. - : IOS Press. - 0921-7126 .- 1875-8452. ; 35:2, s. 87-109
-
Journal article (peer-reviewed)abstract
- Hate speech is a burning issue of today’s society that cuts across numerous strategic areas, including human rights protection, refugee protection, and the fight against racism and discrimination. The gravity of the subject is further demonstrated by António Guterres, the United Nations Secretary-General, calling it “a menace to democratic values, social stability, and peace”. One central platform for the spread of hate speech is the Internet and social media in particular. Thus, automatic detection of hateful and offensive content on these platforms is a crucial challenge that would strongly contribute to an equal and sustainable society when overcome. One significant difficulty in meeting this challenge is collecting sufficient labeled data. In our work, we examine how various resources can be leveraged to circumvent this difficulty. We carry out extensive experiments to exploit various data sources using different machine learning models, including state-of-the-art transformers. We have found that using our proposed methods, one can attain state-of-the-art performance detecting hate speech on Twitter (outperforming the winner of both the HASOC 2019 and HASOC 2020 competitions). It is observed that in general, adding more data improves the performance or does not decrease it. Even when using good language models and knowledge transfer mechanisms, the best results were attained using data from one or two additional data sets.
|
|
| 6. |
|
|
| 7. |
|
|
| 8. |
- Nieves, Juan Carlos
(author)
-
Approximating agreements in formal argumentation dialogues
- 2019
-
In: AI Communications. - : IOS Press. - 0921-7126 .- 1875-8452. ; 32, s. 335-346
-
Journal article (peer-reviewed)abstract
- In many real applications, to reach an agreement between the participants of a dialogue, which can be for instance a negotiation, is not easy. Indeed, there are application domains such as the medical domain where to reach a consensus among medical professionals is not feasible and might be even regarded as counterproductive. In this paper, we introduce an approach for expressing qualitative preferences between the goals of a dialogue considering ordered disjunction rules. By applying argumentation semantics and degrees of satisfaction of goals, we introduce the so-called dialogue agreement degree. Moreover, by considering sets of dialogue agreement degrees, we define a lattice of agreement degrees. We argue that a lattice of agreement degrees suggests different approximations between the current state of a dialogue and its aimed goals; hence, a lattice of agreement degrees can help to define different heuristics in the settings of strategic argumentation.
|
|
| 9. |
- Roy, Debaditya, et al.
(author)
-
Classifying falls using out-of-distribution detection in human activity recognition
- 2023
-
In: AI Communications. - : IOS Press. - 0921-7126 .- 1875-8452. ; 36:4, s. 251-267
-
Journal article (peer-reviewed)abstract
- As the research community focuses on improving the reliability of deep learning, identifying out-of-distribution (OOD) data has become crucial. Detecting OOD inputs during test/prediction allows the model to account for discriminative features unknown to the model. This capability increases the model's reliability since this model provides a class prediction solely at incoming data similar to the training one. Although OOD detection is well-established in computer vision, it is relatively unexplored in other areas, like time series-based human activity recognition (HAR). Since uncertainty has been a critical driver for OOD in vision-based models, the same component has proven effective in time-series applications. In this work, we propose an ensemble-based temporal learning framework to address the OOD detection problem in HAR with time-series data. First, we define different types of OOD for HAR that arise from realistic scenarios. Then we apply our ensemble-based temporal learning framework incorporating uncertainty to detect OODs for the defined HAR workloads. This particular formulation also allows a novel approach to fall detection. We train our model on non-fall activities and detect falls as OOD. Our method shows state-of-The-Art performance in a fall detection task using much lesser data. Furthermore, the ensemble framework outperformed the traditional deep-learning method (our baseline) on the OOD detection task across all the other chosen datasets.
|
|
| 10. |
|
|
