@conference {11, title = {Brain-Like Object Recognition with High-Performing Shallow Recurrent ANNs}, booktitle = {Neural Information Processing Systems}, year = {2019}, abstract = {

Deep convolutional artificial neural networks (ANNs) are the leading class of candidate models of the mechanisms of visual processing in the primate ventral stream. While initially inspired by brain anatomy, over the past years, these ANNs have evolved from a simple eight-layer architecture in AlexNet to extremely deep and branching architectures, demonstrating increasingly better object categorization performance, yet bringing into question how brain-like they still are. In particular, typical deep models from the machine learning community are often hard to map onto the brain\&$\#$39;s anatomy due to their vast number of layers and missing biologically-important connections, such as recurrence. Here we demonstrate that better anatomical alignment to the brain and high performance on machine learning as well as neuroscience measures do not have to be in contradiction. We developed CORnet-S, a shallow ANN with four anatomically mapped areas and recurrent connectivity, guided by Brain-Score, a new large-scale composite of neural and behavioral benchmarks for quantifying the functional fidelity of models of the primate ventral visual stream. Despite being significantly shallower than most models, CORnet-S is the top model on Brain-Score and outperforms similarly compact models on ImageNet. Moreover, our extensive analyses of CORnet-S circuitry variants reveal that recurrence is the main predictive factor of both Brain-Score and ImageNet top-1 performance. Finally, we report that the temporal evolution of the CORnet-S \"IT\" neural population resembles the actual monkey IT population dynamics. Taken together, these results establish CORnet-S, a compact, recurrent ANN, as the current best model of the primate ventral visual stream.

}, doi = {https://papers.nips.cc/paper/9441-brain-like-object-recognition-with-high-performing-shallow-recurrent-anns}, url = {https://papers.nips.cc/paper/9441-brain-like-object-recognition-with-high-performing-shallow-recurrent-anns.pdf}, author = {Jonas Kubilius and Martin Schrimpf and Ha Hong and Najib Majaj and Rajalingham, Rishi and Issa, Elias B. and Kohitij Kar and Bashivan, Pouya and Jonathan Prescott-Roy and Kailyn Schmidt and Aran Nayebi and Daniel Bear and Daniel L. K. Yamins and James J. DiCarlo} } @article {23, title = {CORnet: Modeling the Neural Mechanisms of Core Object Recognition}, journal = {bioRxiv}, year = {2018}, month = {09/2018}, type = {preprint}, abstract = {

Deep artificial neural networks with spatially repeated processing (a.k.a., deep convolutional ANNs) have been established as the best class of candidate models of visual processing in primate ventral visual processing stream. Over the past five years, these ANNs have evolved from a simple feedforward eight-layer architecture in AlexNet to extremely deep and branching NASNet architectures, demonstrating increasingly better object categorization performance and increasingly better explanatory power of both neural and behavioral responses. However, from the neuroscientist\&$\#$39;s point of view, the relationship between such very deep architectures and the ventral visual pathway is incomplete in at least two ways. On the one hand, current state-of-the-art ANNs appear to be too complex (e.g., now over 100 levels) compared with the relatively shallow cortical hierarchy (4-8 levels), which makes it difficult to map their elements to those in the ventral visual stream and to understand what they are doing. On the other hand, current state-of-the-art ANNs appear to be not complex enough in that they lack recurrent connections and the resulting neural response dynamics that are commonplace in the ventral visual stream. Here we describe our ongoing efforts to resolve both of these issues by developing a \"CORnet\" family of deep neural network architectures. Rather than just seeking high object recognition performance (as the state-of-the-art ANNs above), we instead try to reduce the model family to its most important elements and then gradually build new ANNs with recurrent and skip connections while monitoring both performance and the match between each new CORnet model and a large body of primate brain and behavioral data. We report here that our current best ANN model derived from this approach (CORnet-S) is among the top models on Brain-Score, a composite benchmark for comparing models to the brain, but is simpler than other deep ANNs in terms of the number of convolutions performed along the longest path of information processing in the model. All CORnet models are available at\ https://github.com/dicarlolab/CORnet, and we plan to update this manuscript and the available models in this family as they are produced.

}, doi = {https://doi.org/10.1101/408385}, url = {https://www.biorxiv.org/content/10.1101/408385v1.full.pdf}, author = {Kubilius, Jonas and Martin Schrimpf and Aran Nayebi and Daniel Bear and Daniel L. K. Yamins and DiCarlo, James J.} } @article {20, title = {Task-Driven Convolutional Recurrent Models of the Visual System}, journal = {arXiv}, year = {2018}, month = {06/2018}, type = {preprint}, abstract = {

Feed-forward convolutional neural networks (CNNs) are currently state-of-the-art for object classification tasks such as ImageNet. Further, they are quantitatively accurate models of temporally-averaged responses of neurons in the primate brain\&$\#$39;s visual system. However, biological visual systems have two ubiquitous architectural features not shared with typical CNNs: local recurrence within cortical areas, and long-range feedback from downstream areas to upstream areas. Here we explored the role of recurrence in improving classification performance. We found that standard forms of recurrence (vanilla RNNs and LSTMs) do not perform well within deep CNNs on the ImageNet task. In contrast, custom cells that incorporated two structural features, bypassing and gating, were able to boost task accuracy substantially. We extended these design principles in an automated search over thousands of model architectures, which identified novel local recurrent cells and long-range feedback connections useful for object recognition. Moreover, these task-optimized ConvRNNs explained the dynamics of neural activity in the primate visual system better than feedforward networks, suggesting a role for the brain\&$\#$39;s recurrent connections in performing difficult visual behaviors.

}, doi = {https://arxiv.org/abs/1807.00053}, url = {https://arxiv.org/pdf/1807.00053.pdf}, author = {Aran Nayebi and Daniel Bear and Kubilius, Jonas and Ganguli, S and Sussillo, D and DiCarlo, James J. and Yamins, DLK} }