Neuroscience-Inspired Networks for Artificial Intelligence




NINAI


("nai-nai")


WE ARE NEUROSCIENTISTS, PHYSICISTS, MATHEMATICIANS, AND COMPUTER SCIENTISTS FOCUSED ON A SINGLE GOAL:

BRAIN RESEARCH FOR MACHINE INTELLIGENCE TO ENGINEER A LESS ARTIFICAL INTELLIGENCE

WE ARE EMBARKING ON AN INTENSIVE FIVE-YEAR PROJECT FUNDED BY IARPA (MICrONS program)

Team

Andreas Tolias

Principal Investigator

Neuroscience and Computation

Baylor College of Medicine

Xaq Pitkow

Co-principal Investigator

Computational Neuroscience

Baylor College of Medicine

Jake Reimer

Scientific Project Manager

Neuroscience

Baylor College of Medicine

Fabian Sinz

Machine Learning Coordinator

Computational Neuroscience and Machine Learning

University of Tübingen

Ankit Patel

Computational Neuroscience and Machine Learning

Baylor College of Medicine

Chris Xu

Applied Physics

Cornell University

Clay Reid

PI on Connectomics

Neural Circuits and Computations

Allen Institute for Brain Science

Liam Paninski

Computational Neuroscience and Machine Learning

Columbia University

Matthias Bethge

Computational Neuroscience and Machine Learning

University of Tübingen

Nuno Maçarico DaCosta

PI on Connectomics

Light and Electron Microscopy

Allen Institute for Brain Science

Raquel Urtasun

Machine Learning

University of Toronto/Vector Institute

Richard Zemel

Machine Learning

University of Toronto/Vector Institute

Sebstian Seung

PI on Connectomics

Connectomics

Princeton University

Aaron Mok

Cornell University

Alex Ecker

University of Tübingen

Andrea Giovanucci

Flatiron Institute/Simons Foundation

Brendan Celii

Research Assistant

Baylor College of Medicine

Cathryn Cadwell

Student

Baylor College of Medicine

Claudio Michaelis

University of Tübingen

Dimitre Ouzounov

Cornell University

Dimitri Yatsenko

Postdoc

Baylor College of Medicine

Edgar Y Walker

Student

Baylor College of Medicine

Eftychios Pneumatakis

Flatiron Institute/Simons Foundation

Eleni Triantafillou

University of Toronto/Vector Institute

Erick Cobos

Research Associate

Baylor College of Medicine

Eric Wang

Student

Baylor College of Medicine

Federico Scala

Postdoc

Baylor College of Medicine

George Denfield

Student

Baylor College of Medicine

Ivan Ustyuzhaninov

University of Tübingen

Jake Snell

University of Toronto/Vector Institute

James Lucas

University of Toronto/Vector Institute

Jonas Rauber

University of Tübingen

Jörn Jacobsen

University of Tübingen

Josue Ortega Caro

Student

Baylor College of Medicine

Kelly Buchanan

Columbia University

Liza Zhang

University of Toronto/Vector Institute

Manolis Froudarakis

Postdoc

Baylor College of Medicine

Mark Law

University of Toronto/Vector Institute

Mengran Wang

Cornell University

Mengye Ren

University of Toronto/Vector Institute

Paul Fahey

Student

Baylor College of Medicine

Pengcheng Zhou

Columbia University

Philipp Berens

University of Tübingen

Rajkumar Raju

Student

Baylor College of Medicine

Renjie Liao

University of Toronto/Vector Institute

Robin Liu

Baylor College of Medicine

Santiago Cadena

University of Tübingen

Saumil Patel

Baylor College of Medicine

Shan Shen

Postdoc

Baylor College of Medicine

Taliah Muhammad

Lab Technician

Baylor College of Medicine

Tan Nguyen

Rice University

Tianyu Wang

Cornell University

Weili Ni

Student

Baylor College of Medicine

Wieland Brendel

University of Tübingen

Xiaolong Jiang

Baylor College of Medicine

Yang Zhang

Baylor College of Medicine

Zhe Li

Postdoc

Baylor College of Medicine

Zheng Tan

Research Assistant

Baylor College of Medicine

Publications


Edgar Y Walker, R. James Cotton, Wei Ji Ma, Andreas S Tolias (2018) A neural basis of probabilistic computation in visual cortex bioRxiv 365973; doi: https://doi.org/ 10.1101/365973

Gido M. van de Ven, Andreas S. Tolias (2018). Generative replay with feedback connections as a general strategy for continual learning. arXiv: https://arxiv.org/abs/ 1809.10635

Dimitri Yatsenko, Edgar Y. Walker, Andreas S. Tolias (2018) DataJoint: A Simpler Relational Data Model arXiv: https://arxiv.org/abs/1807.11104

Sinz FH, Ecker AS, Fahey PG, Walker EY, Cobos E, Froudarakis E, Yatsenko D, Pitkow X, Reimer J, Tolias AS (2018) Stimulus domain transfer in recurrent models for large scale cortical population prediction on video. NIPS Advances in Neural Information Processing Systems 32. doi:10.1101/452672 URL

Subramaniyan M, Ecker AS, Patel SS, Cotton RJ, Bethge M, Pitkow X, Berens P, Tolias A J (2018) Faster processing of moving compared to flashed bars in awake macaque V1 provides a neural correlate of the flash lag illusion. Journal of Neurophysiol. Aug 22. doi: 10.1152/jn.00792.2017

M. Kümmerer, T. S. A. Wallis, and M. Bethge (2018) Saliency Benchmarking Made Easy: Separating Models, Maps and Metrics The European Conference on Computer Vision (ECCV)

Alexander S. Ecker, Fabian H. Sinz, Emmanouil Froudarakis, Paul G. Fahey, Santiago A. Cadena, Edgar Y. Walker, Erick Cobos, Jacob Reimer, Andreas S. Tolias, Matthias Bethge (2018) A rotation-equivariant convolutional neural network model of primary visual cortex arXiv: https://arxiv.org/abs/1809.10504

A. Mathis, P. Mamidanna, K. Cury, T. Abe, V. Murthy, M. Mathis, and M. Bethge (2018) DeepLabCut: markerless pose estimation of user-defined body parts with deep learning. Nature Neuroscience, 21(9), 1281-1289

S. A. Cadena, M. A. Weis, L. A. Gatys, M. Bethge, and A. S. Ecker (2018) Diverse feature visualizations reveal invariances in early layers of deep neural networks The European Conference on Computer Vision (ECCV)

D. Kobak, M. Weis, and P. Berens (2018) Sparse reduced-rank regression for exploratory visualization of single cell patch-seq recordings bioRxiv

A. Böttcher, W. Brendel, B. Englitz, and M. Bethge (2018) Trace your sources in large-scale data: one ring to find them all arXiv

T. S. A. Wallis, C. M. Funke, A. S. Ecker, L. A. Gatys, F. A. Wichmann, and M. Bethge (2018) Image content is more important than Bouma's Law for scene metamers bioRXiv

W. Brendel, J. Rauber, A. Kurakin, N. Papernot, B. Veliqi, M. Salath\'e, S. P. Mohanty, and M. Bethge (2018) Adversarial Vision Challenge 32nd Conference on Neural Information Processing Systems (NIPS 2018) Competition Track

R. Geirhos, C. R. M. Temme, J. Rauber, H. H. Schütt, M. Bethge, and F. A. Wichmann (2018) Generalisation in humans and deep neural networks Advances in Neural Information Processing Systems 31

L. Schott, J. Rauber, W. Brendel, and M. Bethge (2018) Towards the first adversarially robust neural network model on MNIST arXiv

C. Michaelis, M. Bethge, and A. S. Ecker (2018) One-Shot Segmentation in Clutter ICML

W. Brendel, J. Rauber, and M. Bethge (2018) Decision-Based Adversarial Attacks: Reliable Attacks Against Black-Box Machine Learning Models International Conference on Learning Representations

E. Kelly Buchanan, Ian Kinsella, Ding Zhou, Rong Zhu, Pengcheng Zhou, Felipe Gerhard, John Ferrante, Ying Ma, Sharon Kim, Mohammed Shaik, Yajie Liang, Rongwen Lu, Jacob Reimer, Paul Fahey, Taliah Muhammad, Graham Dempsey, Elizabeth Hillman, Na Ji, Andreas Tolias, Liam Paninski (2018) Penalized matrix decomposition for denoising, compression, and improved demixing of functional imaging data bioRxiv 334706; doi: https://doi.org/10.1101/334706

Denfield GH, Ecker AS, Shinn TJ, Bethge M, Tolias AS (2018) Attentional fluctuations induce shared variability in macaque primary visual cortex Nature Communications. (Jul 9;9(1):2654. doi: 10.1038/s41467-018-05123-6.).

Batty E, Merel J, Brackbill N, Heitman A, Sher A, Litke A, Chichilnisky EJ, Paninski, L, "Multilayer Recurrent Network Models of Primate Retinal Ganglion Cell Responses." Accepted to ICLR 2017 https://openreview.net/forum?id=HkEI22jeg

Berens P, ... Tolias AS, Bethge M (2018) Community-based benchmarking improves spike rate inference from two-photon calcium imaging data. Plos Computational Biology May 21;14(5):e1006157. doi: 10.1371/journal.pcbi.1006157.

Nguyen,T., Baraniuk, R.G., & Patel, A.B. (2018). Semi-Supervised Learning with the Deep Rendering Mixture Model. Submitting to the NIPS 2018.

Nguyen,T., & Patel, A.B. (2018). Use It or Lose It: Neural and Synaptic Pruning Algorithms for Model Selection. Submitted to the International Conference in Machine Learning.

Buesing et al (2017). A Statistical Model of Shared Variability in the Songbird Auditory System. bioRxiv 113670.

Cadwell CR, Scala F, Li S, Livrizzi G., Shen S., Sandberg R, Jiang X & Tolias AS(2017) Multimodal profiling of single-cell morphology, electrophysiology, and gene expression using Patch-seq Nature Protocols. Dec;12(12):2531-2553. doi: 10.1038/nprot.2017.120.

Cadwell CR, Sandberg R, Jiang X, Tolias AS. (2017) Q&A: using Patch-seq to profile single cells. BMC Biol. 2017 Jul 6;15(1):58. doi: 10.1186/s12915-017-0396-0.

Cadwell CR, Palasantza A, Jiang X, Berens P, Deng Q, Yilmaz M, Reimer J, Shen S, Bethge M, Tolias KF, Sandberg R & Tolias AS (2016). Morphological, electrophysiological and transcriptomic profiling of single neurons using Patch-seq. Nature Biotechnology, 34(2), 199-203. doi: 10.1038/nbt.3445. Epub 2015 Dec 21.

S. A. Cadena, G. H. Denfield, E. Y. Walker, L. A. Gatys, A. S. Tolias, M. Bethge, and A. S. Ecker (2017) Deep convolutional models improve predictions of macaque V1 responses to natural images bioRxiv, 2017

Ouzounov DG, Wang T, Wang M, Feng D, Horton NG, Hernández JCC, Cheng Y, Reimer J, Tolias AS, Nishimura N, Xu C (2017) In Vivo Three-Photon Imaging of Activity of GCaMP6-Labeled Neurons in the Hippocampus of Intact Mouse Brain, Nature Methods. Feb 20. doi: 10.1038/nmeth.4183

Carlson, D., Stinson, P., Pakman, A. & Paninski, L. (2016). Partition Functions from Rao- Blackwellized Tempered Sampling. ICML.

Berens et al (2017). Community-based benchmarking improves spike inference from two-photon calcium imaging data. Biorxiv 177956.

Denfield GH, Fahey PG, Reimer J, Tolias AS (2016). Investigating the Limits of Neuromuscular Coupling. Neuron, 7;91(5):954-6

G. H. Denfield, A. S. Ecker, T. J. Shinn, M. Bethge, and A. S. Tolias (2017) Attentional fluctuations induce shared variability in macaque primary visual cortex bioRxiv, 2017

Dordek Y, Soudry D, Meir R, Derdikman D, "Extracting grid cell characteristics from place cell inputs using non-negative principal component analysis." eLife (2016) 5:e10094 doi: http://dx.doi.org/10.7554/eLife.10094

Ecker AS, Denfield GH, Bethge M, Tolias AS (2016). On the Structure of Neuronal Population Activity under Fluctuations in Attentional State. Journal of Neuroscience, 36(5):1775-89. doi: 10.1523/JNEUROSCI.2044-15.2016.

Friedrich, J., Zhou, P., & Paninski, L. (2017). Fast online deconvolution of calcium imaging data. PLoS computational biology, 13(3), e1005423.

Friedrich, J., Yang, W., Soudry, D., Mu, Y., Ahrens, M.B., Yuste, R., Peterka, D.S. and Paninski, L., 2017. Multi-scale approaches for high-speed imaging and analysis of large neural populations. PLoS computational biology, 13(8), p.e1005685.

Gao Y, Archer E, Paninski L, Cunningham J, "Linear dynamical neural population models through nonlinear embeddings", ArXiv (2016) http://arxiv.org/abs/1605.08454 ; NIPS 2016

Giovanucci, A. et al (2017). OnACID: Online Analysis of Calcium Imaging Data in Real Time. NIPS.

Hulse BK, Lubenov EV, Siapas AG (2017) Brain state dependence of hippocampal subthreshold activity in awake mice. Cell Reports 18:136-147. (cover illustration).

Jiang X, Shen S, Sinz F, Reimer J, Cadwell CR, Berens P, Ecker AS, Pater S, Denfield GH, Froudarakis E, Li S, Walker E, Tolias AS (2016). Response to Comment on "Principles of connectivity among morphologically defined cell types in adult neocortex. Science 353(6304):1108.

Jimenez, J. et al (2017). Anxiety cells in a hippocampal-hypothalamic circuit. In press.

W. Brendel, J. Rauber, and M. Bethge Decision-Based Adversarial Attacks: Reliable Attacks Against Black-Box Machine Learning Models arXiv, 2017

S. A. Cadena, G. H. Denfield, E. Y. Walker, L. A. Gatys, A. S. Tolias, M. Bethge, and A. S. Ecker Deep convolutional models improve predictions of macaque V1 responses to natural images bioRxiv, 2017

G. H. Denfield, A. S. Ecker, T. J. Shinn, M. Bethge, and A. S. Tolias Attentional fluctuations induce shared variability in macaque primary visual cortex bioRxiv, 2017

R. Geirhos, D. H. J. Janssen, H. H. Schütt, J. Rauber, M. Bethge, and F. A. Wichmann Comparing deep neural networks against humans: object recognition when the signal gets weaker arXiv, 2017

Klaus et al (2017). The spatiotemporal organization of the striatum encodes action space. Neuron 95: 1171-1180.

D. Klindt, A. S. Ecker, T. Euler, and M. Bethge Neural system identification for large populations separating "what" and "where" Advances in Neural Information Processing Systems 30 (in press), 2017 https://arxiv.org/abs/1711.02653

M. T. Law, Y. Yu, R. Urtasun, R. S. Zemel, E. P. Xing, "Efficient Multiple Instance Metric Learning using Weakly Supervised Data", accepted at CVPR 2017

M. T. Law, R. Urtasun, R. S. Zemel, "Deep Spectral Clustering Learning", accepted at ICML 2017

Li R, Tapaswi R, Liao R, Jia J, Urtasun R, Fidler S. Situation Recognition with Graph Neural Networks, accepted at ICCV, 2017.

Liao R, Schwing A, Zemel R, Urtasun R, "Learning Deep Parsimonious Representations", accepted to NIPS 2016

Linderman, S., Miller, A., Adams, R., Blei, D., Paninski, L., Johnson, M. (2017). Recurrent Switching Linear Dynamical Systems. AISTATS17 / ArXiv 1610.08466.

Luo W, Li, Urtasun R, Zemel R, "Understanding the Effective Receptive Field in Deep Convolutional Neural Networks", accepted to NIPS 2016

Merel J, Shababo B, Naka A, Adesnik H, Paninski L "Bayesian methods for event analysis of intracellular currents", Journal of Neuroscience Methods (2016) 269:21-32 doi: http://dx.doi.org/10.1016/j.jneumeth.2016.05.015

Qi X, Liao R, Jia J, Fidler S, Urtasun R. 3D Graph Neural Networks for RGBD Semantic Segmentation, accepted at ICCV, 2017.

Naka, A. et al (2017). Complementary connectivity defines distinct networks of neocortical somatostatin interneurons. Submitted.

Pakman, A., Gilboa, D., Carlson, D. & Paninski, L. (2017). Stochastic Bouncy Particle Sampler. ICML17 / Arxiv 1609.00770.

Patel A, Nguyen T, Baraniuk R, "A Probabilistic Framework for Deep Learning", accepted to NIPS 2016

Parthasarathy, N., Batty, E. et al (2017). Deep Networks for Decoding Natural Images from Retinal Signals. Biorxiv 153759 / NIPS.

Pitkow X, Angelaki D (2017). Inference in the brain: Statistics flowing in redundant population codes. Neuron. 94(5): 943-53.

Quast KB, Ung K, Froudarakis E, Huang L, Herman I, Addison AP, Ortiz-Guzman J, Cordiner K, Saggau P, Tolias AS, Arenkiel BR. (2017) Developmental broadening of inhibitory sensory maps. Nat Neurosci. 2017 Feb;20(2):189-199. doi: 10.1038/nn. 4467.

Raju R, Pitkow X, "Inference by Reparameterization in Neural Population Codes", ArXiv (2016) http://arxiv.org/abs/1605.06544v1 (accepted to NIPS 2016)

Rahnama Rad, K., Machado, T. & Paninski, L. (2017). Robust and scalable Bayesian analysis of spatial neural tuning function data. Annals of Applied Stat., Arxiv 1606.07845

Sumbul, U., Roossien, D., Chen, F., Barry, N., Boyden, E., Cai, D., Cunningham, J. & Panin- ski, L. (2016). Automated scalable segmentation of neurons from multispectral images. NIPS; Arxiv 1611.00388.

Reimer J, McGinley M, Liu Y, Rodenkirch C, Wang Q, McCormick D, Tolias A, Pupil Fluctuations Track Rapid Changes in Adrenergic and Cholinergic Activity in Cortex, Nature Communications (2016) http://www.nature.com/articles/ncomms13289

Ren M, Zemel R, "End-to- End Instance Segmentation and Counting with Recurrent Attention" accepted at CVPR 2017.

Ren M, Triantafillou E, Ravi S, Snell J, Swersky K, Tenenbaum J, Larochelle H, Zemel R. "Meta Learning for Semi-Supervised Few-Shot Classification". Accepted at NIPS 2017 Workshop on Learning with Limited Labeled Data: Weak Supervision and Beyond and NIPS 2017 Workshop on Meta-Learning.

Sun, R., Archer, E. & Paninski, L. (2017). Variational inference for super resolution microscopy. AISTATS17 / bioRxiv 081703.

Orhan AE, Pitkow X (2017). Skip connections eliminate singularities. arXiv: 1701.09175.

J. Rauber, W. Brendel, and M. Bethge Foolbox v0.8.0: A Python toolbox to benchmark the robustness of machine learning models Reliable Machine Learning in the Wild Workshop, 34th International Conference on Machine Learning, 2017

Ren M, Liao R, Urtasun R, Sinz FH, and Zemel RS "Normalizing the Normalizers: Comparing and Extending Network Normalization Schemes" accepted at ICLR 2017

Snell J,, Swersky K, Zemel R."Prototypical Networks for Few-Shot Learning." accepted at NIPS 2017.

Snell, J, Zemel, RS (2017). "Stochastic segmentation trees." Accepted at UAI 2017.

Yu et al (2017). The central amygdala controls learning in the lateral amygdala. Nature Neuroscience 20: 1680-1685.

Rossant C, Kadir SN, Goodman DFM, Schulman J, Hunter M, Saleem AB, Grosmark A, Belluscio M, Denfield GH, Ecker AS, Tolias AS, Solomon S, Buzsaki G, Carandini M, Harris KD (2016). Spike sorting for large, dense electrode arrays. Nature Neuroscience, 19(4): 623-41

Ren M, Zemel R, "End-to-End Instance Segmentation and Counting with Recurrent Attention: ArXiv (2016) http://arxiv.org/abs/1605.09410

Soudry D, Carmon Y, "No bad local minima: Data independent training error guarantees for multilayer neural networks", ArXiv (2016) http://arxiv.org/abs/1605.08361

Zhou, P. et al (2016+). Efficient and accurate extraction of in vivo calcium signals from microendoscopic video data. Arxiv 1605.07266.

Segev E, Reimer J, Moreaux LC, Fowler TM, Chi D, Sacher WD, Lo M, Deisseroth K, Tolias AS, Faraon A, Roukes ML (2017). Patterned photostimulation via visible-wavelength photonic probes for deep brain optogenetics. Neurophotonics. Jan;4(1):011002

Shan KQ, Lubenov EV, Papadopoulou M, and Siapas AG (2016). Spatial tuning and brain state account for dorsal hippocampal CA1 activity in a non-spatial learning task. eLife, 5, p.e14321. http://dx.doi.org/10.7554/eLife.14321

Taylor G, Burmeister R, Xu Z, Singh B, Patel A, Goldstein T (2016). "Training Neural Networks without Gradients: A Scalable ADMM Approach", https://arxiv.org/abs/1605.02026 (accepted at ICML 2016)

Theis L., Berens P., Froudarakis E., Reimer E., Roson MR., Baden T., Eurler T., Tolias AS., Bethge M (2016). Benchmarking spike reate inference in calcium population imaging. Neuron 90:3:471-82

Wang S, Fidler S, Urtasun R, "Proximal Deep Structured Models", accepted to NIPS 2016

Wu, Urtasun R, Schwing A, "Deep Maximum Margin Clustering", submitted to NIPS 2016


S.A. Cadena, M.A. Weis, L.A. Gatys, M. Bethge, A.S. Ecker: Diverse feature visualizations reveal invariances in early layers of deep neural networks CVPR 2018

Chen, G., Liu, W., Huang, Y., Goel, R., Veeraraghavan, A., & Patel, A.B. (2017). Learning with Retinomorphic Event-Driven Representations for Video Tasks. Submitted to the Conference on Computer Vision and Pattern Recognition.

Law M, Xu J, Urtasun R, Xing, "Efficient Multiple Instance Metric Learning using Weakly Supervised Data", submitted to NIPS 2016

Liao R, Brockschmidt M, Tarlow D, Gaunt A, Urtasun R, Zemel R. Graph Partition Neural Networks for Semi-Supervised Classification, Submitted to ICLR, 2018.

Tianyu Wang, Dimitre G. Ouzounov, Nicholas G. Horton, Bin Zhang, Cheng-Hsun Wu, Yanping Zhang, Mark J. Schnitzer, and Chris Xu, "Three-Photon Imaging of Structure and Neural Activities through Intact Mouse Skull", Nature Methods, Submitted.

Wang T, Liao R, Ba J, Fidler S. NerveNet: Learning Structured Policy with Graph Neural Networks, Submitted to ICLR, 2018.

Wu Y, Ren M, Liao R, Grosse R. Understanding Short-Horizon Bias in Stochastic Meta-Optimization, Submitted to ICLR, 2018.