134 citations · 331 across the 15 of their papers we have counts for
6 papers · 1 filter
On Leakage in Machine Learning Pipelines
Leonard Sasse, Eliana Nicolaisen-Sobesky, Juergen Dukart +9
Machine learning (ML) provides powerful tools for predictive modeling. ML's popularity stems from the promise of sample-level prediction with applications across a variety of field…
Human-in-the-Loop Mixup
Katherine M. Collins, Umang Bhatt, Weiyang Liu +4
Aligning model representations to humans has been found to improve robustness and generalization. However, such methods often focus on standard observational data. Synthetic data i…
Confound-leakage: Confound Removal in Machine Learning Leads to Leakage
Sami Hamdan, Bradley C. Love, Georg G. von Polier +4
Machine learning (ML) approaches to data analysis are now widely adopted in many fields including epidemiology and medicine. To apply these approaches, confounds must first be remo…
Robust priors for regularized regression
Sebastian Bobadilla-Suarez, Matt Jones, Bradley C. Love
Induction benefits from useful priors. Penalized regression approaches, like ridge regression, shrink weights toward zero but zero association is usually not a sensible prior. Insp…
The Costs and Benefits of Goal-Directed Attention in Deep Convolutional Neural Networks
Xiaoliang Luo, Brett D. Roads, Bradley C. Love
People deploy top-down, goal-directed attention to accomplish tasks, such as finding lost keys. By tuning the visual system to relevant information sources, object recognition can…
Learning as the Unsupervised Alignment of Conceptual Systems
Brett D. Roads, Bradley C. Love
Concept induction requires the extraction and naming of concepts from noisy perceptual experience. For supervised approaches, as the number of concepts grows, so does the number of…