@article {181, title = {The Quest for an Integrated Set of Neural Mechanisms Underlying Object Recognition in Primates}, journal = {arXiv}, year = {2023}, month = {12/10/2023}, type = {preprint}, abstract = {

Visual object recognition -- the behavioral ability to rapidly and accurately categorize many visually encountered objects -- is core to primate cognition. This behavioral capability is algorithmically impressive because of the myriad identity-preserving viewpoints and scenes that dramatically change the visual image produced by the same object. Until recently, the brain mechanisms that support that capability were deeply mysterious. However, over the last decade, this scientific mystery has been illuminated by the discovery and development of brain-inspired, image-computable, artificial neural network (ANN) systems that rival primates in this behavioral feat. Apart from fundamentally changing the landscape of artificial intelligence (AI), modified versions of these ANN systems are the current leading scientific hypotheses of an integrated set of mechanisms in the primate ventral visual stream that support object recognition. What separates brain-mapped versions of these systems from prior conceptual models is that they are Sensory-computable, Mechanistic, Anatomically Referenced, and Testable (SMART). Here, we review and provide perspective on the brain mechanisms that the currently leading SMART models address. We review the empirical brain and behavioral alignment successes and failures of those current models. Given ongoing advances in neurobehavioral measurements and AI, we discuss the next frontiers for even more accurate mechanistic understanding. And we outline the likely applications of that SMART-model-based understanding.

}, doi = { https://doi.org/10.48550/arXiv.2312.05956}, url = {https://arxiv.org/pdf/2312.05956.pdf}, author = {Kohitij Kar and James J DiCarlo} } @article {157, title = {Multi-scale hierarchical neural network models that bridge from single neurons in the primate primary visual cortex to object recognition behavior}, journal = {bioRxiv}, year = {2021}, month = {03/01/2021}, type = {preprint}, abstract = {Object recognition relies on inferior temporal (IT) cortical neural population representations that are themselves computed by a hierarchical network of feedforward and recurrently connected neural population called the ventral visual stream (areas V1, V2, V4 and IT). While recent work has created some reasonably accurate image-computable hierarchical neural network models of those neural stages, those models do not yet bridge between the properties of individual neurons and the overall emergent behavior of the ventral stream. For example, current leading ventral stream models do not allow us to ask questions such as: How does the surround suppression behavior of individual V1 neurons ultimately relate to IT neural representation and to behavior?; or How would deactivation of a particular sub-population of V1 neurons specifically alter object recognition behavior? One reason we cannot yet do this is that individual V1 artificial neurons in multi-stage models have not been shown to be functionally similar with individual biological V1 neurons. Here, we took an important first step towards this direction by building and evaluating hundreds of hierarchical neural network models in how well their artificial single neurons approximate macaque primary visual cortical (V1) neurons. We found that single neurons in some models are surprisingly similar to their biological counterparts and that the distributions of single neuron properties, such as those related to orientation and spatial frequency tuning, approximately match those in macaque V1. Crucially, we also observed that hierarchical models with V1-layers that better match macaque V1 at the single neuron level are also more aligned with human object recognition behavior. These results provide the first multi-stage, multi-scale models that allow our field to ask precisely how the specific properties of individual V1 neurons relate to recognition behavior. Finally, we here show that an optimized classical neuroscientific model of V1 is still more functionally similar to primate V1 than all of the tested multi-stage models, suggesting that further model improvements are possible, and that those improvements would likely have tangible payoffs in terms of behavioral prediction accuracy and behavioral robustness.Single neurons in some image-computable hierarchical neural network models are functionally similar to single neurons in macaque primate visual cortex (V1)Some hierarchical neural networks models have V1 layers that better match the biological distributions of macaque V1 single neuron response propertiesMulti-stage hierarchical neural network models with V1 stages that better match macaque V1 are also more aligned with human object recognition behavior at their output stageCompeting Interest StatementThe authors have declared no competing interest.}, doi = {10.1101/2021.03.01.433495}, author = {Tiago Marques and Martin Schrimpf and James J DiCarlo} } @conference {169, title = {Neural Population Geometry Reveals the Role of Stochasticity in Robust Perception}, booktitle = {Neural Information Processing Systems (NeurIPS)}, year = {2021}, address = {Lisbon, Portugal}, abstract = {

Adversarial examples are often cited by neuroscientists and machine learning researchers as an example of how computational models diverge from biological sensory systems. Recent work has proposed adding biologically-inspired components to visual neural networks as a way to improve their adversarial robustness. One surprisingly effective component for reducing adversarial vulnerability is response stochasticity, like that exhibited by biological neurons. Here, using recently developed geometrical techniques from computational neuroscience, we investigate how adversarial perturbations influence the internal representations of standard, adversarially trained, and biologically-inspired stochastic networks. We find distinct geometric signatures for each type of network, revealing different mechanisms for achieving robust representations. Next, we generalize these results to the auditory domain, showing that neural stochasticity also makes auditory models more robust to adversarial perturbations. Geometric analysis of the stochastic networks reveals overlap between representations of clean and adversarially perturbed stimuli, and quantitatively demonstrate that competing geometric effects of stochasticity mediate a tradeoff between adversarial and clean performance. Our results shed light on the strategies of robust perception utilized by adversarially trained and stochastic networks, and help explain how stochasticity may be beneficial to machine and biological computation.

}, url = {https://proceedings.neurips.cc/paper/2021/file/8383f931b0cefcc631f070480ef340e1-Paper.pdf}, author = {Joel Dapello and Jenelle Feather and Tiago Marques and David Cox and Josh McDermott and James J DiCarlo and Sueyeon Chung} }