An official website of the United States government
Abstract Adaptivity in advanced learning technologies offer the possibility to adapt to different student backgrounds, which is difficult to do in a traditional classroom setting. However, there are mixed results on the effectiveness of adaptivity based on different implementations and contexts. In this paper, we introduce AI adaptivity in the context of a new genre of Intelligent Science Stations that bring intelligent tutoring into the physical world. Intelligent Science Stations are mixed-reality systems that bridge the physical and virtual worlds to improve children’s inquiry-based STEM learning. Automated reactive guidance is made possible by a specialized AI computer vision algorithm, providing personalized interactive feedback to children as they experiment and make discoveries in their physical environment. We report on a randomized controlled experiment where we compare learning outcomes of children interacting with the Intelligent Science Station that has task-loop adaptivity incorporated, compared to another version that provides tasks randomly without adaptivity. Our results show that adaptivity using Bayesian Knowledge Tracing in the context of a mixed-reality system leads to better learning of scientific principles, without sacrificing enjoyment. These results demonstrate benefits of adaptivity in a mixed-reality setting to improve children’s science learning.
more »
« less
Harmonized mutual development through exploring and creating sound
The science of sound presents a holistic learning opportunity to engage embodied intelligence and lived experience in mutually shared soundscapes where material objects become sites for the pursuit of curiosity and aesthetic beauty. When young people are presented with this view of the realm of science learning and practice, the possibility for alignment and harmony between personal knowing, social relations, and a living environment can emerge. And even more compelling, the possibility for what we describe as harmonized mutual development in a community of learners moves within reach. This paper explores the potential of a curricular and pedagogical design to produce a kind of collective ethic in learning that is often elusive in formal learning environments.
more »
« less
- Award ID(s):
- 1657366
- PAR ID:
- 10414875
- Editor(s):
- Chinn, C.
- Date Published:
- Journal Name:
- Proceedings of the 16th International Conference of the Learning Sciences - ICLS 2022 (pp. 871-878). International Society of the Learning Sciences.
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
The Python Foundations seminar emphasizes a hands-on approach and is designed to reach a diverse student population to provide them with the entry-level programming skills required in data science. The creation of the seminar materials has been funded by a three-year federal grant and has followed a systematic approach to enhance the student learning experience and raise student awareness of data science. The seminar materials—structured in three parts: pre-seminar, live seminar, and post-seminar—are licensed under the Creative Commons Attribution-ShareAlike 4.0 International license to encourage adoption by any institution. To foster interest in the seminar, students have the possibility to earn a digital badge attesting to their newly acquired skills.more » « less
-
ABSTRACT Although the brain is often characterized as a complex system, theoretical and philosophical frameworks often struggle to capture this. For example, mainstream mechanistic accounts model neural systems as fixed and static in ways that fail to capture their dynamic nature and large set of possible behaviors. In this paper, we provide a framework for capturing a common type of complex system in neuroscience, which involves two main aspects: (i) constraints on the system and (ii) the system's possibility space of available outcomes. Our analysis merges neuroscience examples with recent work in the philosophy of science to suggest that the possibility space concept involves two essential types of constraints, which we call hard and soft constraints. Our analysis focuses on a domain‐general notion of possibility space that is present in manifold frameworks and representations, phase space diagrams in dynamical systems theory, and paradigmatic cases, such as Waddington's epigenetic landscape model. After building the framework with such cases, we apply it to three main examples in neuroscience: adaptability, resilience, and phenomenology. We explore how this framework supports a philosophical toolkit for neuroscience and how it helps advance recent work in the philosophy of science on constraints, scientific explanations, and impossibility explanations. We show how fruitful connections between neuroscience and philosophy can support conceptual clarity, theoretical advances, and the identification of similar systems across different domains in neuroscience.more » « less
-
The social impacts of computer technology are often glorified in public discourse, but there is growing concern about its actual effects on society. In this article, we ask: how does “consent” as an analytical framework make visible the social dynamics and power relations in the capture, extraction, and labor of data science knowledge production? We hypothesize that a form of boundary violation in data science workplaces—gender harassment—may correlate with the ways humans’ lived experiences are extracted to produce Big Data. The concept of consent offers a useful way to draw comparisons between gender relations in data science and the means by which machines are trained to learn and reason. Inspired by how Big Tech leaders describe unsupervised machine learning, and the co-optation of “revolutionary” rhetoric they use to do so, we introduce a concept we call “techniques of invisibility.” Techniques of invisibility are the ways in which an extreme imbalance between exposure and opacity, demarcated along fault lines of power, are fabricated and maintained, closing down the possibility for bidirectional transparency in the production and applications of algorithms. Further, techniques of invisibility, which we group into two categories—epistemic injustice and the Brotherhood—include acts of subjection by powerful actors in data science designed to quell resistance to exploitative relations. These techniques may be useful in making further connections between epistemic violence, sexism, and surveillance, sussing out persistent boundary violations in data science to render the social in data science visible, and open to scrutiny and debate.more » « less
-
Convex Q-learning is a recent approach to reinforcement learning, motivated by the possibility of a firmer theory for convergence, and the possibility of making use of greater a priori knowledge regarding policy or value function structure. This paper explores algorithm design in the continuous time domain, with a finite-horizon optimal control objective. The main contributions are (i) The new Q-ODE: a model-free characterization of the Hamilton-Jacobi-Bellman equation. (ii) A formulation of Convex Q-learning that avoids approximations appearing in prior work. The Bellman error used in the algorithm is defined by filtered measurements, which is necessary in the presence of measurement noise. (iii) Convex Q-learning with linear function approximation is a convex program. It is shown that the constraint region is bounded, subject to an exploration condition on the training input. (iv) The theory is illustrated in application to resource allocation for distributed energy resources, for which the theory is ideally suited.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Conference Paper:
- The DOI is not currently available.
