Two questions have guided my scientific research:
1. How does network structure influence computational function in neural systems?
2. How can complex systems use experience to improve performance?
Most of these publications can also be accessed via Google Scholar.
Publications:
[37] Light-microscopy based dense connectomic reconstruction of mammalian brain tissue
Tavakoli, et al.
bioRxiv, 2024
[paper]
[36] How AI could lead to a better understanding of the brain
Jain.
Nature, 2023
[paper]
[35] Multi-Layered Maps of Neuropil with Segmentation-Guided Contrastive Learning
Dorkenwald, et al.
Nature Methods, 2023
[paper]
[34] Mapping of neuronal and glial primary cilia contactome and connectome in the human cerebral cortex
Wu, et al.
Neuron, 2023
[paper]
[33] A large-scale volumetric correlated light and electron microscopy study localizes Alzheimer’s disease-related molecules in the hippocampus
Han, et al.
bioRxiv, 2023
[paper]
[32] Probing Molecular Diversity and Ultrastructure of Brain Cells with Fluorescent Aptamers
Lu, et al.
bioRxiv, 2023
[paper]
[31] Multiplexed Volumetric CLEM enabled by antibody derivatives provides new insights into the cytology of the mouse cerebellar cortex
Han, et al.
bioRxiv, 2023
[paper]
[30] SyConn2: Dense synaptic connectivity inference for volume EM
Schubert, et al.
Nature Methods, 2022
[paper]
[29] Structured sampling of olfactory input by the fly mushroom body
Zheng, et al.
Current Biology, 2022
[paper]
[28] Denoising-based Image Compression for Connectomics
Minnen, et al.
bioRxiv, 2021
[paper and blog post]
[27] A connectomic study of a petascale fragment of human cerebral cortex
Shapson-Coe, et al.
bioRxiv, 2021
[paper and blog post and publicly accessible data] [press: quanta, bloomberg, new scientist, technology review, others]
[26] The Mind of a Mouse
Abbott, et al.
Cell, 2020
[paper]
[25] Neuronal Subcompartment Classification and Merge Error Correction
Li, Januszewski, Jain, and Li.
MICCAI 2020
[paper]
[24] An anatomical substrate of credit assignment in reinforcement learning
Kornfeld, Januszewski, Schubert, Jain, Denk, and Fee.
bioRxiv, 2020
[paper]
[23] A Connectome and Analysis of the Adult Drosophila Central Brain
Scheffer, et al.
eLife, 2020
[paper and publicly accessible connectome] [press: nytimes, wired, hhmi, others]
[22] Automated Reconstruction of a Serial-Section EM Drosophila Brain with Flood-Filling Networks and Local Realignment
Li, Lindsey, Januszewski, Zheng, Bates, Taisz, Tyka, Nichols, Li, Perlman, Maitin-Shepard, Blakely, Leavitt, Jefferis, Bock, and Jain
bioRxiv, 2019
[paper and publicly accessible reconstruction]
[21] Learning cellular morphology with neural networks
Schubert, Dorkenwald, Januszewski, Jain, and Kornfeld.
Nature Communications, 2019
[paper]
[20] Segmentation-Enhanced CycleGAN
Januszewski and Jain.
bioRxiv, 2019
[paper]
[19] High-Precision Automated Reconstruction of Neurons with Flood-filling Networks
Januszewski, Kornfeld, Li, Pope, Blakely, Lindsey, Maitin-Shepard, Tyka, Denk, and Jain.
Nature Methods, 2018
[paper, open-access bioRxiv pre-print, code, Google AI blog post]
[18] Adversarial Image Alignment and Interpolation
Jain.
arXiv pre-print, 2017
[paper]
[17] Morphological Error Detection in 3D Segmentations
Rolnick, Meirovitch, Parag, Pfister, Jain, Lichtman, Boyden, Shavit.
arXiv pre-print, 2017
[paper]
[16] Superhuman Accuracy on the SNEMI3D Connectomics Challenge
Lee, Zung, Li, Jain, and Seung.
arXiv pre-print, 2017
[paper]
[15] Flood-filling Networks.
Januszewski, Maitin-Shepard, Li, Kornfeld, Denk, and Jain.
arXiv pre-print, 2016
[paper]
[14] Combinatorial Energy Learning for Image Segmentation.
Maitin-Shepard, Jain, Januszewski, Li, and Abbeel.
Advances in Neural Information Processing Systems 29 [NIPS 2016]
[paper]
[13] Deep and Wide Multiscale Recursive Networks for Robust Image Labeling.
Huang and Jain.
International Conference on Learning Representations [ICLR 2014; Conference Track]
[paper]
[12] Learned versus Hand-Designed Feature Representations for 3d Agglomeration.
Bogovic, Huang, and Jain.
International Conference on Learning Representations [ICLR 2014; Conference Track & Oral]
[paper]
[11] Connectomic reconstruction of the inner plexiform layer in the mouse retina.
Helmstaedter, Briggman, Turaga, Jain, Seung, and Denk.
Nature, 2013
[paper]
[10] Learning to Agglomerate Superpixel Hierarchies.
Jain, Turaga, Briggman, Helmstaedter, Denk, and Seung.
Advances in Neural Information Processing Systems 24 [NIPS 2011]
[paper]
[9] Machines that learn to segment images: a crucial technology for connectomics.
Jain, Seung, and Turaga.
Current Opinion in Neurobiology, 2010
[paper]
[8] Boundary Learning by Optimization with Topological Constraints.
Jain, Bollmann, Richardson, Berger, Helmstaedter, Briggman, Denk, Bowden, Mendenhall, Abraham, Harris, Kasthuri, Hayworth, Schalek, Tapia, Lichtman, and Seung.
IEEE Conference on Computer Vision and Pattern Recognition [CVPR 2010]
[paper] [supplementary: specific methods]
[7] Convolutional networks can learn to generate affinity graphs for image segmentation.
Turaga, Murray, Jain, Roth, Helmstaedter, Briggman, Denk, and Seung.
Neural Computation, 2010
[paper]
[6] Machine Learning of Image Analysis with Convolutional Networks and Topological Constraints.
PhD Dissertation, Massachusetts Institute of Technology, 2009
[thesis]
[5] Natural Image Denoising with Convolutional Networks.
Jain and Seung.
Advances in Neural Information Processing Systems 21 [NIPS 2008]
[paper] [sample implementation: archive, readme]
[4] Supervised Learning of Image Restoration with Convolutional Networks.
Jain, Murray, Roth, Turaga, Zhigulin, Briggman, Helmstaedter, Denk, and Seung.
International Conference on Computer Vision [ICCV 2007]
[paper] [supplementary: specific methods]
[3] Representing Part-Whole Relations in Recurrent Neural Networks.
Jain, Zhigulin, and Seung.
Advances in Neural Information Processing Systems 18 [NIPS 2005]
[paper]
[2] Exploratory analysis and visualization of speech and music by locally linear embedding.
Jain and Saul.
International Conf. on Speech, Acoustics, & Signal Processing [ICASSP 2004]
[paper]
[1] A Smorgasbord of Features for Statistical Machine Translation.
Och, Gildea, Khudanpur, Sarkar, Yamada, Fraser, Kumar, Shen, Smith, Eng, Jain, Jin, and Radev.
Human Language Technology and 5th Meeting of the NAACL [HLT-NAACL 2004]
[paper]