J
James Gornet
Researcher at California Institute of Technology
Publications - 12
Citations - 49
James Gornet is an academic researcher from California Institute of Technology. The author has contributed to research in topics: Penetrance & X-inactivation. The author has an hindex of 4, co-authored 9 publications receiving 28 citations. Previous affiliations of James Gornet include Columbia University & Cold Spring Harbor Laboratory.
Papers
More filters
Proceedings Article
Neural Networks with Recurrent Generative Feedback
Yujia Huang,James Gornet,Sihui Dai,Zhiding Yu,Tan Nguyen,Doris Y. Tsao,Animashree Anandkumar +6 more
TL;DR: The proposed framework, termed Convolutional Neural Networks with Feedback (CNN-F), introduces a generative feedback with latent variables into existing CNN architectures, making consistent predictions via alternating MAP inference under a Bayesian framework.
Posted Content
Reconstructing neuronal anatomy from whole-brain images
James Gornet,Kannan Umadevi Venkataraju,Arun Narasimhan,Nicholas L. Turner,Kisuk Lee,H. Sebastian Seung,Pavel Osten,Uygar Sümbül +7 more
TL;DR: In this paper, the authors presented connectivity-preserving methods and data augmentation strategies for supervised learning of neuroanatomy from light microscopy using neural networks and demonstrated a scalable, distributed implementation that can reconstruct the large datasets that sub-micron whole-brain images produce.
Proceedings ArticleDOI
Reconstructing Neuronal Anatomy from Whole-Brain Images
James Gornet,Kannan Umadevi Venkataraju,Arun Narasimhan,Nicholas L. Turner,Kisuk Lee,H. Sebastian Seung,Pavel Osten,Uygar Sümbül +7 more
TL;DR: Connectivity-preserving methods and data augmentation strategies for supervised learning of neuroanatomy from light microscopy using neural networks are presented and a scalable, distributed implementation that can reconstruct the large datasets that sub-micron whole-brain images produce is demonstrated.
Posted Content
Neural Networks with Recurrent Generative Feedback
Yujia Huang,James Gornet,Sihui Dai,Zhiding Yu,Tan Nguyen,Doris Y. Tsao,Animashree Anandkumar +6 more
TL;DR: In this article, the authors propose Convolutional Neural Networks with Feedback (CNN-F) to enforce self-consistency in neural networks by incorporating generative recurrent feedback, where consistent predictions are made through alternating MAP inference under a Bayesian framework.
Proceedings ArticleDOI
Development of brain templates for whole brain atlases
TL;DR: This paper describes the framework that each experimenter to create a template brain registered with the Allen CCF for their unique combination and develops a new CCF brain template for processing and analysis of the UClear brains.