More Like this

1. Learning and Animal Movement

   https://doi.org/10.3389/fevo.2021.681704  

   Lewis, Mark A.; Fagan, William F.; Auger-Méthé, Marie; Frair, Jacqueline; Fryxell, John M.; Gros, Claudius; Gurarie, Eliezer; Healy, Susan D.; Merkle, Jerod A. (July 2021, Frontiers in Ecology and Evolution)

   null (Ed.)

   Integrating diverse concepts from animal behavior, movement ecology, and machine learning, we develop an overview of the ecology of learning and animal movement. Learning-based movement is clearly relevant to ecological problems, but the subject is rooted firmly in psychology, including a distinct terminology. We contrast this psychological origin of learning with the task-oriented perspective on learning that has emerged from the field of machine learning. We review conceptual frameworks that characterize the role of learning in movement, discuss emerging trends, and summarize recent developments in the analysis of movement data. We also discuss the relative advantages of different modeling approaches for exploring the learning-movement interface. We explore in depth how individual and social modalities of learning can matter to the ecology of animal movement, and highlight how diverse kinds of field studies, ranging from translocation efforts to manipulative experiments, can provide critical insight into the learning process in animal movement. 

   more » « less
2. Learning Trajectories Through Learning Making and Engineering, and Implications

   Lande, Micah (July 2021, American Society for Engineering Education)

   This NSF EEC EAGER research project investigates how undergraduate STEM and engineering students’ learning trajectories evolve over time, from 1st year to senior year, along a novice to expert spectrum. We borrow the idea of “learning trajectories” from mathematics education that can paint the evolution of students’ knowledge and skills over time over a set of learning experiences. We use a theoretical framework based on adaptive expertise and design thinking adaptive expertise to further advance a design learning continuum. 

   more » « less
3. Convex and Bilevel Optimization for Neural-Symbolic Inference and Learning

   Dickens, Charles Andrew; Gao, Changyu; Pryor, Connor; Wright, Stephen; Getoor, Lise (July 2024, Proceedings of Machine Learning Research (ICML))

   We leverage convex and bilevel optimization techniques to develop a general gradient-based parameter learning framework for neural-symbolic (NeSy) systems. We demonstrate our framework with NeuPSL, a state-of-the-art NeSy architecture. To achieve this, we propose a smooth primal and dual formulation of NeuPSL inference and show learning gradients are functions of the optimal dual variables. Additionally, we develop a dual block coordinate descent algorithm for the new formulation that naturally exploits warm-starts. This leads to over $$100 \times$$ learning runtime improvements over the current best NeuPSL inference method. Finally, we provide extensive empirical evaluations across $$8$$ datasets covering a range of tasks and demonstrate our learning framework achieves up to a $16$ 

   more » « less
4. Investigating the intensity and integration of active learning and lecture.

   https://doi.org/10.1037/mac0000160  

   Martella, Amedee Marchand; Schneider, Darryl W; O'Day, Garrett M; Karpicke, Jeffrey D (February 2024, Journal of Applied Research in Memory and Cognition)

   Given that the active learning literature lacks systematic investigations on how the intensity and integration of lecture and active learning affects learning, we conducted two experiments to examine the impact of these variables. The first experiment involved 146 participants who learned about biological taxonomies through pure lecture or pure active learning. Participants in the pure lecture condition scored significantly higher on a posttest than those in the pure active learning condition. The second experiment involved 219 participants who learned about biological taxonomies through pure lecture, a lecture and active learning activity that were interspersed, or a lecture and active learning activity that were blocked. Participants in the interspersed condition scored significantly higher than participants in the blocked and pure lecture conditions (which did not significantly differ). Based on these experiments, it may not be a question of either/or but rather a question of how to integrate lecture and active learning. 

   more » « less
5. Reset It and Forget It: Relearning Last-Layer Weights Improves Continual and Transfer Learning

   https://doi.org/10.3233/FAIA240840  

   Frati, Lapo; Traft, Neil; Clune, Jeff; Cheney, Nick (October 2024, IOS Press)

   This work identifies a simple pre-training mechanism that leads to representations exhibiting better continual and transfer learning. This mechanism—the repeated resetting of weights in the last layer, which we nickname “zapping”—was originally designed for a meta-continual-learning procedure, yet we show it is surprisingly applicable in many settings beyond both meta-learning and continual learning. In our experiments, we wish to transfer a pre-trained image classifier to a new set of classes, in few shots. We show that our zapping procedure results in improved transfer accuracy and/or more rapid adaptation in both standard fine-tuning and continual learning settings, while being simple to implement and computationally efficient. In many cases, we achieve performance on par with state of the art meta-learning without needing the expensive higher-order gradients by using a combination of zapping and sequential learning. An intuitive explanation for the effectiveness of this zapping procedure is that representations trained with repeated zapping learn features that are capable of rapidly adapting to newly initialized classifiers. Such an approach may be considered a computationally cheaper type of, or alternative to, meta-learning rapidly adaptable features with higher-order gradients. This adds to recent work on the usefulness of resetting neural network parameters during training, and invites further investigation of this mechanism. 

   more » « less