An official website of the United States government
We propose an algorithm, guided variational autoencoder (Guided-VAE), that is able to learn a controllable generative model by performing latent representation disentanglement learning. The learning objective is achieved by providing signals to the latent encoding/embedding in VAE without changing its main backbone architecture, hence retaining the desirable properties of the VAE. We design an unsupervised strategy and a supervised strategy in Guided-VAE and observe enhanced modeling and controlling capability over the vanilla VAE. In the unsupervised strategy, we guide the VAE learning by introducing a lightweight decoder that learns latent geometric transformation and principal components; in the supervised strategy, we use an adversarial excitation and inhibition mechanism to encourage the disentanglement of the latent variables. Guided-VAE enjoys its transparency and simplicity for the general representation learning task, as well as disentanglement learning. On a number of experiments for representation learning, improved synthesis/sampling, better disentanglement for classification, and reduced classification errors in meta learning have been observed.
more »
« less
Creating Opportunities for Transactive Exchange for Learning in Performance-Oriented Team Projects
Pursuing productivity, students often adopt a divide-and-conquer strategy that undercuts collaborative learning opportunities. In this study, we introduce a task structuring and role scaffolding paradigm to create opportunities for transactive exchange in such performance-oriented tasks and experimentally compare two prompting strategies -- one designed to create a focused discussion and another to intensify transactivity -- while controlling for time on task. We find significant learning gains of each strategy when used separately, but not in tandem.
more »
« less
- PAR ID:
- 10174699
- Date Published:
- Journal Name:
- The Interdisciplinarity of the Learning Sciences, 14th International Conference of the Learning Sciences (ICLS)
- Volume:
- 3
- Page Range / eLocation ID:
- 1719-1720
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
Lamberg, Teruni; Moss, Diana (Ed.)Building Thinking Classrooms (Liljedahl, 2021) provides teachers with a new method of designing and sequencing tasks called “thin slicing,” which emerged from variation theory. The results of the present study indicate that an analysis of the dimensions and ranges of variation within such a task offers insights into learning opportunities available. Specifically, identifying instances where variation has not been adequately positioned against a background of sameness can highlight potentially limited opportunities for students to notice the intended mathematics. The results of this analysis can inform design decisions and modifications to the task before implementation increasing the potential of the task to support student learning.more » « less
-
Chinn, C; Tan, E; Chan, C; Kali, Y (Ed.)Robotics activities can provide students with opportunities to engage in computational thinking (CT) as well as support disciplinary learning goals. The goal of the Robots in Science project is to create, implement, and refine a PD program for middle school science teachers to design and implement robotics and CT-integrated science lessons. Two case studies illustrate how teachers used robotics activities to provide opportunities for science learning.more » « less
-
Chinn, C; Tan, E; Chan, C; Kali, Y (Ed.)Robotics activities can provide students with opportunities to engage in computational thinking (CT) as well as support disciplinary learning goals. The goal of the Robots in Science project is to create, implement, and refine a PD program for middle school science teachers to design and implement robotics and CT-integrated science lessons. Two case studies illustrate how teachers used robotics activities to provide opportunities for science learning.more » « less
-
Chinn, C; Tan, E; Chan, C; Kali, Y (Ed.)Robotics activities can provide students with opportunities to engage in computational thinking (CT) as well as support disciplinary learning goals. The goal of the Robots in Science project is to create, implement, and refine a PD program for middle school science teachers to design and implement robotics and CT-integrated science lessons. Two case studies illustrate how teachers used robotics activities to provide opportunities for science learning.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Conference Paper:
- The DOI is not currently available.
