More Like this

1. Assessing the Effectiveness of Teaching Basic Programming Skills Using Hands-On versus Web-based Activities

   Pham, Vincent; Mehicevic, Ammar; Lam, Tony; Rubio, Kevin; Robertson, Cindy; Doloc-Mihu, Anca (March 2025, Association for the Advancement of Computing in Education (AACE))

   This paper describes a study about which medium best introduces programming concepts to those without programming knowledge, a blocked coded robot (Cozmo) or online Scratch coding. Participants were taught basic coding concepts such as if statements and while loops in both instances and given a task to test their newly attained knowledge. Results showed that even though Scratch coding on computers was more successful as a tool to teach students programming concepts, the Cozmo robot brought more engagement and interest to the students. 

   more » « less
2. Few Is Enough: Task-Augmented Active Meta-learning for Brain Cell Classification

   https://doi.org/10.1007/978-3-030-59710-8_36  

   Yuan, Pengyu; Mobiny, Aryan; Jahanipour, Jahandar; Li, Xiaoyang; Cicalese, Pietro; Roysam, Badrinath; Patel, Vishal; Dragan, Maric; Nguyen, Hien V. (January 2020, Medical Image Computing and Computer Assisted Intervention)

   null (Ed.)

   Deep Neural Networks (or DNNs) must constantly cope with distribution changes in the input data when the task of interest or the data collection protocol changes. Retraining a network from scratch to combat this issue poses a significant cost. Meta-learning aims to deliver an adaptive model that is sensitive to these underlying distribution changes, but requires many tasks during the meta-training process. In this paper, we propose a tAsk-auGmented actIve meta-LEarning (AGILE) method to efficiently adapt DNNs to new tasks by using a small number of training examples. AGILE combines a meta-learning algorithm with a novel task augmentation technique which we use to generate an initial adaptive model. It then uses Bayesian dropout uncertainty estimates to actively select the most difficult samples when updating the model to a new task. This allows AGILE to learn with fewer tasks and a few informative samples, achieving high performance with a limited dataset. We perform our experiments using the brain cell classification task and compare the results to a plain meta-learning model trained from scratch. We show that the proposed task-augmented meta-learning framework can learn to classify new cell types after a single gradient step with a limited number of training samples. We show that active learning with Bayesian uncertainty can further improve the performance when the number of training samples is extremely small. Using only 1% of the training data and a single update step, we achieved 90% accuracy on the new cell type classification task, a 50% points improvement over a state-of-the-art meta-learning algorithm. 

   more » « less
3. Practical galaxy morphology tools from deep supervised representation learning

   https://doi.org/10.1093/mnras/stac525  

   Walmsley, Mike; Scaife, Anna M; Lintott, Chris; Lochner, Michelle; Etsebeth, Verlon; Géron, Tobias; Dickinson, Hugh; Fortson, Lucy; Kruk, Sandor; Masters, Karen L; et al (May 2022, Monthly Notices of the Royal Astronomical Society)

   ABSTRACT Astronomers have typically set out to solve supervised machine learning problems by creating their own representations from scratch. We show that deep learning models trained to answer every Galaxy Zoo DECaLS question learn meaningful semantic representations of galaxies that are useful for new tasks on which the models were never trained. We exploit these representations to outperform several recent approaches at practical tasks crucial for investigating large galaxy samples. The first task is identifying galaxies of similar morphology to a query galaxy. Given a single galaxy assigned a free text tag by humans (e.g. ‘#diffuse’), we can find galaxies matching that tag for most tags. The second task is identifying the most interesting anomalies to a particular researcher. Our approach is 100 per cent accurate at identifying the most interesting 100 anomalies (as judged by Galaxy Zoo 2 volunteers). The third task is adapting a model to solve a new task using only a small number of newly labelled galaxies. Models fine-tuned from our representation are better able to identify ring galaxies than models fine-tuned from terrestrial images (ImageNet) or trained from scratch. We solve each task with very few new labels; either one (for the similarity search) or several hundred (for anomaly detection or fine-tuning). This challenges the longstanding view that deep supervised methods require new large labelled data sets for practical use in astronomy. To help the community benefit from our pretrained models, we release our fine-tuning code zoobot. Zoobot is accessible to researchers with no prior experience in deep learning. 

   more » « less
4. Sequencing, Task Failures, and Capacity When Failures Are Driven by a Non‐Homogeneous Poisson Process

   https://doi.org/10.1002/nav.22235  

   Zhu, Lingjiong; Paul, Anand; Aytug, Haldun (June 2025, Naval Research Logistics (NRL))

   ABSTRACT We study the optimal sequencing of a batch of tasks on a machine subject to random disruptions driven by a non‐homogeneous Poisson process (NHPP), such that every disruption requires the interrupted task to be re‐processed from scratch, and partially completed work on a disrupted task is wasted. The NHPP models random disruptions whose frequency varies systematically with time. In general, the time taken to process a given batch of tasks depends on the order in which the tasks are processed. We find conditions under which the simplest possible sequencing rules—shortest processing time first (SPT) and longest processing time first (LPT)—suffice to minimize the completion time of a batch of tasks. 

   more » « less
5. Zero Experience Required: Plug & Play Modular Transfer Learning for Semantic Visual Navigation

   https://doi.org/10.1109/CVPR52688.2022.01652  

   Al-Halah, Ziad; Ramakrishnan, Santhosh K.; Grauman, Kristen (June 2022, IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR))

   In reinforcement learning for visual navigation, it is common to develop a model for each new task, and train that model from scratch with task-specific interactions in 3D environments. However, this process is expensive; massive amounts of interactions are needed for the model to generalize well. Moreover, this process is repeated when-ever there is a change in the task type or the goal modality. We present a unified approach to visual navigation using a novel modular transfer learning model. Our model can effectively leverage its experience from one source task and apply it to multiple target tasks (e.g., ObjectNav, Room-Nav, Vi ewNav) with various goal modalities (e.g., image, sketch, audio, label). Furthermore, our model enables zero-shot experience learning, whereby it can solve the target tasks without receiving any task-specific interactive training. Our experiments on multiple photorealistic datasets and challenging tasks show that our approach learns faster, generalizes better, and outperforms SoTA models by a significant margin. 

   more » « less