| 1. |
- Ferrari, Lucia, et al.
(författare)
-
A topological model for partial equivariance in deep learning and data analysis
- 2023
-
Ingår i: Frontiers in Artificial Intelligence. - : Frontiers Media SA. - 2624-8212. ; 6
-
Tidskriftsartikel (refereegranskat)abstract
- In this article, we propose a topological model to encode partial equivariance in neural networks. To this end, we introduce a class of operators, called P-GENEOs, that change data expressed by measurements, respecting the action of certain sets of transformations, in a non-expansive way. If the set of transformations acting is a group, we obtain the so-called GENEOs. We then study the spaces of measurements, whose domains are subjected to the action of certain self-maps and the space of P-GENEOs between these spaces. We define pseudo-metrics on them and show some properties of the resulting spaces. In particular, we show how such spaces have convenient approximation and convexity properties.
|
|
| 2. |
- Hellström, Thomas
(författare)
-
AI and its consequences for the written word
- 2023
-
Ingår i: Frontiers in Artificial Intelligence. - : Frontiers Media S.A.. - 2624-8212. ; 6
-
Tidskriftsartikel (refereegranskat)abstract
- The latest developments of chatbots driven by Large Language Models (LLMs), more specifically ChatGPT, have shaken the foundations of how text is created, and may drastically reduce and change the need, ability, and valuation of human writing. Furthermore, our trust in the written word is likely to decrease, as an increasing proportion of all written text will be AI-generated – and potentially incorrect. In this essay, I discuss these implications and possible scenarios for us humans, and for AI itself.
|
|
| 3. |
- Kilic, Kaan, et al.
(författare)
-
Argument-based human–AI collaboration for supporting behavior change to improve health
- 2023
-
Ingår i: Frontiers in Artificial Intelligence. - : Frontiers Media S.A.. - 2624-8212. ; 6
-
Tidskriftsartikel (refereegranskat)abstract
- This article presents an empirical requirement elicitation study for an argumentation-based digital companion for supporting behavior change, whose ultimate goal is the promotion and facilitation of healthy behavior. The study was conducted with non-expert users as well as with health experts and was in part supported by the development of prototypes. It focuses on human-centric aspects, in particular user motivations, as well as on expectations and perceptions regarding the role and interaction behavior of a digital companion. Based on the results of the study, a framework for person tailoring the agent's roles and behaviors, and argumentation schemes are proposed. The results indicate that the extent to which a digital companion argumentatively challenges or supports a user's attitudes and chosen behavior and how assertive and provocative the companion is may have a substantial and individualized effect on user acceptance, as well as on the effects of interacting with the digital companion. More broadly, the results shed some initial light on the perception of users and domain experts of “soft,” meta-level aspects of argumentative dialogue, indicating potential for future research.
|
|
| 4. |
- Mahmoud, Sara, 1988-, et al.
(författare)
-
How to train a self-driving vehicle : On the added value (or lack thereof) of curriculum learning and replay buffers
- 2023
-
Ingår i: Frontiers in Artificial Intelligence. - : Frontiers Media S.A.. - 2624-8212. ; 6
-
Tidskriftsartikel (refereegranskat)abstract
- Learning from only real-world collected data can be unrealistic and time consuming in many scenario. One alternative is to use synthetic data as learning environments to learn rare situations and replay buffers to speed up the learning. In this work, we examine the hypothesis of how the creation of the environment affects the training of reinforcement learning agent through auto-generated environment mechanisms. We take the autonomous vehicle as an application. We compare the effect of two approaches to generate training data for artificial cognitive agents. We consider the added value of curriculum learning—just as in human learning—as a way to structure novel training data that the agent has not seen before as well as that of using a replay buffer to train further on data the agent has seen before. In other words, the focus of this paper is on characteristics of the training data rather than on learning algorithms. We therefore use two tasks that are commonly trained early on in autonomous vehicle research: lane keeping and pedestrian avoidance. Our main results show that curriculum learning indeed offers an additional benefit over a vanilla reinforcement learning approach (using Deep-Q Learning), but the replay buffer actually has a detrimental effect in most (but not all) combinations of data generation approaches we considered here. The benefit of curriculum learning does depend on the existence of a well-defined difficulty metric with which various training scenarios can be ordered. In the lane-keeping task, we can define it as a function of the curvature of the road, in which the steeper and more occurring curves on the road, the more difficult it gets. Defining such a difficulty metric in other scenarios is not always trivial. In general, the results of this paper emphasize both the importance of considering data characterization, such as curriculum learning, and the importance of defining an appropriate metric for the task.
|
|
