Suggested further readings

Pytorch - papers:

Automatic differentiation library; some tutorials openreview.net/pdf?id=BJJsrmfCZ.

Recommended review papers:

Richards, B. A., Lillicrap, T. P., Beaudoin, P., Bengio, Y., Bogacz, R., Christensen, A., …, and Kording, K. P. (2019). A deep learning framework for neuroscience. Nature neuroscience, 22(11), 1761-1770. doi: 10.1038/s41593-019-0520-2 (postprint: www.ncbi.nlm.nih.gov/pmc/articles/PMC7115933 ).

Lindsay, G. W. (2021). Convolutional neural networks as a model of the visual system: Past, present, and future. Journal of cognitive neuroscience, 33(10), 2017-2031. doi: 10.1162/jocn_a_01544 (preprint: arxiv.org/pdf/2001.07092 ).

Intro:

Large list of papers comparing DNNs and the brain:

Cichy, R. M., Khosla, A., Pantazis, D., Torralba, A., and Oliva, A. (2016). Comparison of deep neural networks to spatio-temporal cortical dynamics of human visual object recognition reveals hierarchical correspondence. Scientific reports, 6(1), 1-13. doi: 10.1038/srep27755 .

Hasson, U., Nastase, S. A., & Goldstein, A. (2020). Direct fit to nature: an evolutionary perspective on biological and artificial neural networks. Neuron, 105(3), 416-434. doi: 10.1016/j.neuron.2019.12.002 .

Heuer, K., Gulban, O. F., Bazin, P. L., Osoianu, A., Valabregue, R., Santin, M., …, and Toro, R. (2019). Evolution of neocortical folding: A phylogenetic comparative analysis of MRI from 34 primate species. Cortex, 118, 275-291. doi: 10.1016/j.cortex.2019.04.011 .

Zhou, B., Khosla, A., Lapedriza, A., Oliva, A., and Torralba, A. (2015). Object detectors emerge in deep scene cnns. In ICLR, San Diego, CA, USA. arXiv:1412.6856.

Zhou, B., Bau, D., Oliva, A., and Torralba, A. (2018). Interpreting deep visual representations via network dissection. IEEE transactions on pattern analysis and machine intelligence, 41(9), 2131-2145. doi: 10.1109/TPAMI.2018.2858759 .

Tutorials:

Dataset:

Stringer, C., Michaelos, M., Tsyboulski, D., Lindo, S. E., and Pachitariu, M. (2021). High-precision coding in visual cortex. Cell, 184(10), 2767–2778.e15. doi: 10.1016/j.cell.2021.03.042 (preprint: www.biorxiv.org/content/biorxiv/early/2019/11/04/679324.full.pdf ).

Deep learning used for encoding models:

Batty, E., Merel, J., Brackbill, N., Heitman, A., Sher, A., Litke, A., …, and Paninski, L. (2017). Multilayer recurrent network models of primate retinal ganglion cell responses. ICLR 2017, Toulon, France.

Cadena, S. A., Denfield, G. H., Walker, E. Y., Gatys, L. A., Tolias, A. S., Bethge, M., and Ecker, A. S. (2019). Deep convolutional models improve predictions of macaque V1 responses to natural images. PLoS computational biology, 15(4), e1006897. doi: 10.1371/journal.pcbi.1006897 .

McIntosh, L., Maheswaranathan, N., Nayebi, A., Ganguli, S., and Baccus, S. (2016). Deep learning models of the retinal response to natural scenes. Advances in neural information processing systems, 29.

Walker, E. Y., Sinz, F. H., Cobos, E., Muhammad, T., Froudarakis, E., Fahey, P. G., …, and Tolias, A. S. (2019). Inception loops discover what excites neurons most using deep predictive models. Nature neuroscience, 22(12), 2060-2065. doi: 10.1038/s41593-019-0517-x .

Comparing deep networks and the brain:

Guclu, U., and van Gerven, M. A. (2015). Deep neural networks reveal a gradient in the complexity of neural representations across the ventral stream. Journal of Neuroscience, 35(27), 10005-10014. doi: 10.1523/JNEUROSCI.5023-14.2015 .

Khaligh-Razavi, S. M., and Kriegeskorte, N. (2014). Deep supervised, but not unsupervised, models may explain IT cortical representation. PLoS computational biology, 10(11), e1003915. doi: 10.1371/journal.pcbi.1003915 .

Kriegeskorte, N., Mur, M., and Bandettini, P. A. (2008). Representational similarity analysis-connecting the branches of systems neuroscience. Frontiers in systems neuroscience, 2, 4. doi: 10.3389/neuro.06.004.2008 .

Mohsenzadeh, Y., Mullin, C., Lahner, B., and Oliva, A. (2020). Emergence of Visual center-periphery Spatial organization in Deep convolutional neural networks. Scientific Reports, 10(1), 1-8. doi: 10.1038/s41598-020-61409-0 .

Yamins, D. L., Hong, H., Cadieu, C. F., Solomon, E. A., Seibert, D., & DiCarlo, J. J. (2014). Performance-optimized hierarchical models predict neural responses in higher visual cortex. Proceedings of the national academy of sciences, 111(23), 8619-8624. doi: 10.1073/pnas.1403112111 (postprint: europepmc.org/articles/pmc4060707?pdf=render ).

Deep learning:

Goh, G. (2017). Why momentum really works. Distill, 2(4), e6. doi: 10.23915/distill.00006 .

He, K., Zhang, X., Ren, S., and Sun, J. (2016). Deep residual learning for image recognition. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 770-778).

Ioffe, S., and Szegedy, C. (2015). Batch normalization: Accelerating deep network training by reducing internal covariate shift. In International conference on machine learning (pp. 448-456). PMLR.

Li, H., Xu, Z., Taylor, G., Studer, C., & Goldstein, T. (2018). Visualizing the loss landscape of neural nets. Advances in neural information processing systems, 31.

Nielsen, M. (2016). A visual proof that neural nets can compute any function. URL: neuralnetworksanddeeplearning.com/chap4.html.

Olah, C. (2014). Conv nets: A modular perspective. URL: colah.github.io/posts/2014-07-Conv-Nets-Modular.

Outro 1

Jozwik, K. M., Kriegeskorte, N., Storrs, K. R., and Mur, M. (2017). Deep convolutional neural networks outperform feature-based but not categorical models in explaining object similarity judgments. Frontiers in psychology, 8, 1726. doi: 10.3389/fpsyg.2017.01726 .

Kriegeskorte, N., and Douglas, P. K. (2018). Cognitive computational neuroscience. Nature neuroscience, 21(9), 1148-1160. doi: 10.1038/s41593-018-0210-5 (postprint: europepmc.org/articles/pmc6706072?pdf=render ).

Kietzmann, T. C., Spoerer, C. J., Sörensen, L. K., Cichy, R. M., Hauk, O., and Kriegeskorte, N. (2019). Recurrence is required to capture the representational dynamics of the human visual system. Proceedings of the National Academy of Sciences, 116(43), 21854-21863. doi: 10.1073/pnas.1905544116 .

Kubilius, J., Schrimpf, M., Kar, K., Rajalingham, R., Hong, H., Majaj, N., …, and DiCarlo, J. J. (2019). Brain-like object recognition with high-performing shallow recurrent ANNs. Advances in neural information processing systems, 32.

Lillicrap, T. P., Santoro, A., Marris, L., Akerman, C. J., and Hinton, G. (2020). Backpropagation and the brain. Nature reviews. Neuroscience, 21(6), 335–346. doi: 10.1038/s41583-020-0277-3 (preprint: ora.ox.ac.uk/objects/uuid:862189c1-0088-4f78-b17a-2748c2019209/download_file?safe_filename=Lillicrap_v6_2020.pdf&file_format=pdf&type_of_work=Journal+article ).

Nili, H., Wingfield, C., Walther, A., Su, L., Marslen-Wilson, W., and Kriegeskorte, N. (2014). A toolbox for representational similarity analysis. PLoS computational biology, 10(4), e1003553. doi: 10.1371/journal.pcbi.1003553 .

Schrimpf, M., Kubilius, J., Hong, H., Majaj, N. J., Rajalingham, R., Issa, E. B., …, and DiCarlo, J. J. (2020). Brain-score: Which artificial neural network for object recognition is most brain-like?. BioRxiv, 407007. doi: 10.1101/407007 .

Spoerer, C. J., Kietzmann, T. C., Mehrer, J., Charest, I., and Kriegeskorte, N. (2020). Recurrent neural networks can explain flexible trading of speed and accuracy in biological vision. PLoS computational biology, 16(10), e1008215. doi: 10.1371/journal.pcbi.1008215 .

Storrs, K. R., Kietzmann, T. C., Walther, A., Mehrer, J., and Kriegeskorte, N. (2021). Diverse deep neural networks all predict human inferior temporal cortex well, after training and fitting. Journal of Cognitive Neuroscience, 33(10), 2044-2064. doi: 10.1162/jocn_a_01755 (postprint: repository.ubn.ru.nl/bitstream/handle/2066/237374/1/237374.pdf ).

Tang, H., Schrimpf, M., Lotter, W., Moerman, C., Paredes, A., Caro, J. O., … & Kreiman, G. (2018). Recurrent computations for visual pattern completion. Proceedings of the National Academy of Sciences, 115(35), 8835-8840. doi: 10.1073/pnas.1719397115 .

Outro 2

Chambers, C., Seethapathi, N., Saluja, R., Loeb, H., Pierce, S. R., Bogen, D. K., … & Kording, K. P. (2020). Computer vision to automatically assess infant neuromotor risk. IEEE Transactions on Neural Systems and Rehabilitation Engineering, 28(11), 2431-2442. doi: 10.1109/TNSRE.2020.3029121 (postprint: www.ncbi.nlm.nih.gov/pmc/articles/PMC8011647 ).