@article {165, title = {Chemogenetic suppression of macaque V4 neurons produces retinotopically specific deficits in downstream IT neural activity patterns and core object recognition behavior}, journal = {Journal of Vision}, volume = {21}, year = {2021}, pages = {2489-2489}, abstract = {

Distributed activity patterns across multiple brain areas (e.g., V4, IT) enable primates to accurately identify visual objects. To strengthen our inferences about the causal role of underlying brain circuits, it is necessary to develop targeted neural perturbation strategies that enable discrimination amongst competing models. To probe the role of area V4 in core object recognition, we expressed inhibitory DREADDs in neurons within a 5x5 mm subregion of V4 cortex via multiple viral injections (AAV8-hSyn-hM4Di-mCherry; two macaques). To assay for successful neural suppression, we recorded from a multi-electrode array implanted over the transfected V4. We also recorded from multi-electrode arrays in the IT cortex (the primary feedforward target of V4), while simultaneously measuring the monkeys\’ behavior during object discrimination tasks. We found that systemic (intramuscular) injection of the DREADDs activator (CNO) produced reversible reductions (~20\%) in image-evoked V4 responses compared to the control condition (saline injections). Monkeys showed significant behavioral performance deficits upon CNO injections (compared to saline), which were larger when the object position overlapped with the RF estimates of the transfected V4 neurons. This is consistent with the hypothesis that the suppressed V4 neurons are critical to this behavior. Furthermore, we observed commensurate deficits in the linearly-decoded estimates of object identity from the IT population activity (post-CNO). To model the perturbed brain circuitry, we used a primate brain-mapped artificial neural network (ANN) model (CORnet-S) that supports object recognition. We \“lesioned\” the model\’s corresponding V4 subregion by modifying its weights such that the responses matched a subset of our experimental V4 measurements (post-CNO). Indeed, the lesioned model better predicted the measured (held-out) V4 and IT responses (post-CNO), compared to the model\&$\#$39;s non-lesioned version, validating our approach. In the future, our approach allows us to discriminate amongst competing mechanistic brain models, while the data provides constraints to guide more accurate alternatives.

}, doi = {https://doi.org/10.1167/jov.21.9.2489}, author = {Kar, Kohitij and Schrimpf, Martin and Schmidt, Kailyn and DiCarlo, JJ} } @article {4, title = {Evidence that recurrent circuits are critical to the ventral stream{\textquoteright}s execution of core object recognition behavior}, journal = {Nature Neuroscience}, volume = {22}, year = {2019}, month = {01/2019}, pages = {974 - 983}, issn = {1097-6256}, doi = {10.1038/s41593-019-0392-5}, url = {http://www.nature.com/articles/s41593-019-0392-5}, author = {Kar, Kohitij and Kubilius, Jonas and Schmidt, Kailyn and Issa, Elias B. and DiCarlo, James J.} } @conference {166, title = {Using Brain-Score to Evaluate and Build Neural Networks for Brain-Like Object Recognition}, booktitle = {Computational and Systems Neuroscience (COSYNE)}, year = {2019}, address = {Denver, CO}, author = {Schrimpf, Martin and Kubilius, Jonas and Hong, Ha and Majaj, Najib and Rajalingham, Rishi and Issa, Elias B and Kar, Kohitij and Ziemba, Corey M and Bashivan, Pouya and Prescott-Roy, Jonathan and Schmidt, Kailyn and Yamins, Daniel LK and DiCarlo, James J} } @article {22, title = {Brain-Score: Which Artificial Neural Network for Object Recognition is most Brain-Like?}, journal = {bioRxiv}, year = {2018}, month = {09/2018}, type = {preprint}, abstract = {

The internal representations of early deep artificial neural networks (ANNs) were found to be remarkably similar to the internal neural representations measured experimentally in the primate brain. Here we ask, as deep ANNs have continued to evolve, are they becoming more or less brain-like? ANNs that are most functionally similar to the brain will contain mechanisms that are most like those used by the brain. We therefore developed Brain-Score - a composite of multiple neural and behavioral benchmarks that score any ANN on how similar it is to the brain\&$\#$39;s mechanisms for core object recognition - and we deployed it to evaluate a wide range of state-of-the-art deep ANNs. Using this scoring system, we here report that: (1) DenseNet-169, CORnet-S and ResNet-101 are the most brain-like ANNs. (2) There remains considerable variability in neural and behavioral responses that is not predicted by any ANN, suggesting that no ANN model has yet captured all the relevant mechanisms. (3) Extending prior work, we found that gains in ANN ImageNet performance led to gains on Brain-Score. However, correlation weakened at \>= 70\% top-1 ImageNet performance, suggesting that additional guidance from neuroscience is needed to make further advances in capturing brain mechanisms. (4) We uncovered smaller (i.e. less complex) ANNs that are more brain-like than many of the best-performing ImageNet models, which suggests the opportunity to simplify ANNs to better understand the ventral stream. The scoring system used here is far from complete. However, we propose that evaluating and tracking model-benchmark correspondences through a Brain-Score that is regularly updated with new brain data is an exciting opportunity: experimental benchmarks can be used to guide machine network evolution, and machine networks are mechanistic hypotheses of the brain\&$\#$39;s network and thus drive next experiments. To facilitate both of these, we release Brain-Score.org: a platform that hosts the neural and behavioral benchmarks, where ANNs for visual processing can be submitted to receive a Brain-Score and their rank relative to other models, and where new experimental data can be naturally incorporated.

}, doi = {https://doi.org/10.1101/407007}, url = {https://www.biorxiv.org/content/10.1101/407007v2.full.pdf}, author = {Martin Schrimpf and Kubilius, Jonas and Ha Hong and Najib Majaj and Rajalingham, Rishi and Issa, Elias B. and Kar, Kohitij and Bashivan, Pouya and Jonathan Prescott-Roy and Schmidt, Kailyn and Daniel L. K. Yamins and DiCarlo, James J.} } @article {19, title = {Evidence that recurrent circuits are critical to the ventral stream{\textquoteright}s execution of core object recognition behavior}, journal = {bioRxiv}, year = {2018}, month = {06/2018}, type = {preprint}, abstract = {

Non-recurrent deep convolutional neural networks (DCNNs) are currently the best models of core object recognition; a behavior supported by the densely recurrent primate ventral stream, culminating in the inferior temporal (IT) cortex. Are these recurrent circuits critical to ventral stream\&$\#$39;s execution of this behavior? We reasoned that, if recurrence is critical, then primates should outperform feedforward-only DCNNs for some images, and that these images should require additional processing time beyond the feedforward IT response. Here we first used behavioral methods to discover hundreds of these \"challenge\" images. Second, using large-scale IT electrophysiology in animals performing core recognition tasks, we observed that behaviorally-sufficient, linearly-decodable object identity solutions emerged ~30ms (on average) later in IT for challenge images compared to DCNN and primate performance-matched \"control\" images. We observed these same late solutions even during passive viewing. Third, consistent with a failure of feedforward computations, the behaviorally-critical late-phase IT population response patterns evoked by the challenge images were poorly predicted by DCNN activations. Interestingly, deeper CNNs better predicted these late IT responses, suggesting a functional equivalence between recurrence and additional nonlinear transformations. Our results argue that automatically-evoked recurrent circuits are critical even for rapid object identification. By precisely comparing current DCNNs, primate behavior and IT population dynamics, we provide guidance for future recurrent model development.

}, doi = {https://doi.org/10.1101/354753}, url = {https://www.biorxiv.org/content/10.1101/354753v1.full.pdf}, author = {Kar, Kohitij and Kubilius, Jonas and Schmidt, Kailyn and Issa, Elias B and DiCarlo, James J.} } @article {13, title = {Large-Scale, High-Resolution Comparison of the Core Visual Object Recognition Behavior of Humans, Monkeys, and State-of-the-Art Deep Artificial Neural Networks}, journal = {The Journal of Neuroscience}, volume = {38}, year = {2018}, month = {03/2019}, pages = {7255 - 7269}, abstract = {

Primates-including humans-can typically recognize objects in visual images at a glance even in spite of naturally occurring identity-preserving image transformations (e.g. changes in viewpoint). A primary neuroscience goal is to uncover neuron-level mechanistic models that quantitatively explain this behavior by predicting primate performance for each and every image. Here, we applied this stringent behavioral prediction test to the leading mechanistic models of primate vision (specifically, deep, convolutional, artificial neural networks; ANNs) by directly comparing their behavioral signatures against those of humans and rhesus macaque monkeys. Using high-throughput data collection systems for human and monkey psychophysics, we collected over one million behavioral trials from 1472 anonymous humans and five male macaque monkeys for 2400 images over 276 binary object discrimination tasks. Consistent with previous work, we observed that state-of-the-art deep, feed-forward convolutional ANNs trained for visual categorization (termed DCNN models) accurately predicted primate patterns of object-level confusion. However, when we examined behavioral performance for individual images within each object discrimination task, we found that all tested DCNN models were significantly non-predictive of primate performance, and that this prediction failure was not accounted for by simple image attributes, nor rescued by simple model modifications. These results show that current DCNN models cannot account for the image-level behavioral patterns of primates, and that new ANN models are needed to more precisely capture the neural mechanisms underlying primate object vision. To this end, large-scale, high-resolution primate behavioral benchmarks-such as those obtained here-could serve as direct guides for discovering such models.Recently, specific feed-forward deep convolutional artificial neural networks (ANNs) models have dramatically advanced our quantitative understanding of the neural mechanisms underlying primate core object recognition. In this work, we tested the limits of those ANNs by systematically comparing the behavioral responses of these models with the behavioral responses of humans and monkeys, at the resolution of individual images. Using these high-resolution metrics, we found that all tested ANN models significantly diverged from primate behavior. Going forward, these high-resolution, large-scale primate behavioral benchmarks could serve as direct guides for discovering better ANN models of the primate visual system.

}, issn = {0270-6474}, doi = {10.1523/JNEUROSCI.0388-18.2018}, url = {http://www.jneurosci.org/content/38/33/7255}, author = {Rajalingham, Rishi and Issa, Elias B. and Bashivan, Pouya and Kar, Kohitij and Schmidt, Kailyn and DiCarlo, James J.} } @article {21, title = {Large-scale, high-resolution comparison of the core visual object recognition behavior of humans, monkeys, and state-of-the-art deep artificial neural networks}, journal = {bioRxiv}, year = {2018}, month = {02/2018}, type = {preprint}, abstract = {

Primates\—including humans\—can typically recognize objects in visual images at a glance even in the face of naturally occurring identity-preserving image transformations (e.g. changes in viewpoint). A primary neuroscience goal is to uncover neuron-level mechanistic models that quantitatively explain this behavior by predicting primate performance for each and every image. Here, we applied this stringent behavioral prediction test to the leading mechanistic models of primate vision (specifically, deep, convolutional, artificial neural networks; ANNs) by directly comparing their behavioral signatures against those of humans and rhesus macaque monkeys. Using high-throughput data collection systems for human and monkey psychophysics, we collected over one million behavioral trials for 2400 images over 276 binary object discrimination tasks. Consistent with previous work, we observed that state-of-the-art deep, feed-forward convolutional ANNs trained for visual categorization (termed DCNNIC\ models) accurately predicted primate patterns of object-level confusion. However, when we examined behavioral performance for individual images within each object discrimination task, we found that all tested DCNNIC\ models were significantly non-predictive of primate performance, and that this prediction failure was not accounted for by simple image attributes, nor rescued by simple model modifications. These results show that current DCNNIC\ models cannot account for the image-level behavioral patterns of primates, and that new ANN models are needed to more precisely capture the neural mechanisms underlying primate object vision. To this end, large-scale, high-resolution primate behavioral benchmarks\—such as those obtained here\—could serve as direct guides for discovering such models.

}, doi = {https://doi.org/10.1101/240614}, url = {https://www.biorxiv.org/content/10.1101/240614v4.full.pdf}, author = {Rajalingham, Rishi and Issa, Elias B and Bashivan, Pouya and Kar, Kohitij and Schmidt, Kailyn and DiCarlo, James J.} }