arXiv subjects

Michael J. Tarr

Publications and source records attributed to Michael J. Tarr.

22 records · Page 2Linked to original sources

arXiv2020

Learning Intermediate Features of Object Affordances with a Convolutional Neural Network

Our ability to interact with the world around us relies on being able to infer what actions objects afford -- often referred to as affordances. The neural mechanisms of object-action associations are realized in the visuomotor pathway where information about both visual properties and actions is integrated into common representations. However, explicating these mechanisms is particularly challenging in the case of affordances because there is hardly any one-to-one mapping between visual features and inferred actions. To better understand the nature of affordances, we trained a deep convolutional neural network (CNN) to recognize affordances from images and to learn the underlying features or the dimensionality of affordances. Such features form an underlying compositional structure for the general representation of affordances which can then be tested against human neural data. We view this representational analysis as the first step towards a more formal account of how humans perceive and interact with the environment.

q-bio.NC↗

arXiv2018

BOLD5000: A public fMRI dataset of 5000 images

Vision science, particularly machine vision, has been revolutionized by introducing large-scale image datasets and statistical learning approaches. Yet, human neuroimaging studies of visual perception still rely on small numbers of images (around 100) due to time-constrained experimental procedures. To apply statistical learning approaches that integrate neuroscience, the number of images used in neuroimaging must be significantly increased. We present BOLD5000, a human functional MRI (fMRI) study that includes almost 5,000 distinct images depicting real-world scenes. Beyond dramatically increasing image dataset size relative to prior fMRI studies, BOLD5000 also accounts for image diversity, overlapping with standard computer vision datasets by incorporating images from the Scene UNderstanding (SUN), Common Objects in Context (COCO), and ImageNet datasets. The scale and diversity of these image datasets, combined with a slow event-related fMRI design, enable fine-grained exploration into the neural representation of a wide range of visual features, categories, and semantics. Concurrently, BOLD5000 brings us closer to realizing Marr's dream of a singular vision science - the intertwined study of biological and computer vision.

q-bio.NC↗

arXiv2016

Temporal and Semantic Effects on Multisensory Integration

How do we integrate modality-specific perceptual information arising from the same physical event into a coherent percept? One possibility is that observers rely on information across perceptual modalities that shares temporal structure and/or semantic associations. To explore the contributions of these two factors in multisensory integration, we manipulated the temporal and semantic relationships between auditory and visual information produced by real-world events, such as paper tearing or cards being shuffled. We identified distinct neural substrates for integration based on temporal structure as compared to integration based on event semantics. Semantically incongruent events recruited left frontal regions, while temporally asynchronous events recruited right frontal cortices. At the same time, both forms of incongruence recruited subregions in the temporal, occipital, and lingual cortices. Finally, events that were both temporally and semantically congruent modulated activity in the parahippocampus and anterior temporal lobe. Taken together, these results indicate that low-level perceptual properties such as temporal synchrony and high-level knowledge such as semantics play a role in our coherent perceptual experience of physical events.

q-bio.NC↗

arXiv2015

Estimating Learning Effects: A Short-Time Fourier Transform Regression Model for MEG Source Localization

Magnetoencephalography (MEG) has a high temporal resolution well-suited for studying perceptual learning. However, to identify where learning happens in the brain, one needs to ap- ply source localization techniques to project MEG sensor data into brain space. Previous source localization methods, such as the short-time Fourier transform (STFT) method by Gramfort et al.([Gramfort et al., 2013]) produced intriguing results, but they were not designed to incor- porate trial-by-trial learning effects. Here we modify the approach in [Gramfort et al., 2013] to produce an STFT-based source localization method (STFT-R) that includes an additional regression of the STFT components on covariates such as the behavioral learning curve. We also exploit a hierarchical L 21 penalty to induce structured sparsity of STFT components and to emphasize signals from regions of interest (ROIs) that are selected according to prior knowl- edge. In reconstructing the ROI source signals from simulated data, STFT-R achieved smaller errors than a two-step method using the popular minimum-norm estimate (MNE), and in a real-world human learning experiment, STFT-R yielded more interpretable results about what time-frequency components of the ROI signals were correlated with learning.

stat.AP↗