Ruairidh McLennan Battleday

Ruairidh McLennan Battleday
Princeton University | PU · Department of Computer Science

BM BCh Graduate-Entry Medicine (Oxon)

About

13
Publications
4,519
Reads
How we measure 'reads'
A 'read' is counted each time someone views a publication summary (such as the title, abstract, and list of authors), clicks on a figure, or views or downloads the full-text. Learn more
383
Citations
Citations since 2016
10 Research Items
376 Citations
2016201720182019202020212022020406080100
2016201720182019202020212022020406080100
2016201720182019202020212022020406080100
2016201720182019202020212022020406080100
Introduction
Ruairidh McLennan Battleday currently works at the Department of Computer Science, Princeton University. Ruairidh does research in Computational Cognitive Science, Machine Learning, and Artificial Intelligence. His current project is 'Leveraging deep neural networks to study human cognition', along with Josh Peterson and Tom Griffiths.

Publications

Publications (13)
Article
Full-text available
The remarkable successes of convolutional neural networks (CNNs) in modern computer vision are by now well known, and they are increasingly being explored as computational models of the human visual system. In this paper, we ask whether CNNs might also provide a basis for modeling higher-level cognition, focusing on the core phenomena of similarity...
Article
Full-text available
Human categorization is one of the most important and successful targets of cognitive modeling, with decades of model development and assessment using simple, low-dimensional artificial stimuli. However, it remains unclear how these findings relate to categorization in more natural settings, involving complex, high-dimensional stimuli. Here, we tak...
Preprint
Full-text available
Traditional models of category learning in psychology focus on representation at the category level as opposed to the stimulus level, even though the two are likely to interact. The stimulus representations employed in such models are either hand-designed by the experimenter, inferred circuitously from human judgments, or borrowed from pretrained d...
Preprint
Full-text available
Much of human learning and inference can be framed within the computational problem of relational generalization. In this project, we propose a Bayesian model that generalizes relational knowledge to novel environments by analogically weighting predictions from previously encountered relational structures. First, we show that this learner outperfor...
Conference Paper
The classification performance of deep neural networks has begun to asymptote at near-perfect levels. However, their ability to generalize outside the training set and their robustness to adversarial attacks have not. In this paper , we make progress on this problem by training with full label distributions that reflect human perceptual uncertainty...
Preprint
The classification performance of deep neural networks has begun to asymptote at near-perfect levels. However, their ability to generalize outside the training set and their robustness to adversarial attacks have not. In this paper, we make progress on this problem by training with full label distributions that reflect human perceptual uncertainty....
Preprint
Human categorization is one of the most important and successful targets of cognitive modeling in psychology, yet decades of development and assessment of competing models have been contingent on small sets of simple, artificial experimental stimuli. Here we extend this modeling paradigm to the domain of natural images, revealing the crucial role t...
Conference Paper
The classification performance of deep neural networks has begun to asymptote at near-perfect levels. However, their ability to generalize outside the training set and their robustness to adversarial attacks have not. In this paper, we make progress on this problem by training with full label distributions that reflect human perceptual uncertainty....
Article
Full-text available
Over the last few decades, psychologists have developed sophisticated formal models of human categorization using simple artificial stimuli. In this paper, we use modern machine learning methods to extend this work into the realm of naturalistic stimuli, enabling human categorization to be studied over the complex visual domain in which it evolved...
Article
Full-text available
Modafinil is an FDA-approved eugeroic that directly increases cortical catecholamine levels, indirectly upregulates cerebral serotonin, glutamate, orexin, and histamine levels, and indirectly decreases cerebral gamma-amino-butrytic acid levels. In addition to its approved use treating excessive somnolence, modafinil is thought to be used widely off...
Article
Full-text available
In recent decades, our appreciation of the complexity of the brain has deepened immensely, as has our understanding of how it performs key functions. In the face of such complexity, and given the rising cost of neuropsychiatric illness (1), an intriguing question is whether we can promote further understanding, and in some cases enhancement, of the...
Poster
Our conclusion: it is clear that the proportion of OOHCA survivors admitted to hospital has increased over the last decade, accompanied by significant improvements in survival measures. We posit that these data reflect an optimistic cultural shift in resuscitation and admission practice, which has in turn positively affected outcome measures. Likel...

Network

Cited By