Zobrazeno 1 - 10
of 33
pro vyhledávání: '"Huang, Gary B."'
We propose a method to facilitate exploration and analysis of new large data sets. In particular, we give an unsupervised deep learning approach to learning a latent representation that captures semantic similarity in the data set. The core idea is t
Externí odkaz:
http://arxiv.org/abs/2012.12175
Extracting a connectome from an electron microscopy (EM) data set requires identification of neurons and determination of synapses between neurons. As manual extraction of this information is very time-consuming, there has been extensive research eff
Externí odkaz:
http://arxiv.org/abs/1604.03075
Autor:
Zhao, Ting, Takemura, Shin-ya, Huang, Gary B., Horne, Jane Anne, Katz, William T., Shinomiya, Kazunori, Scheffer, Louis K., Meinertzhagen, Ian A., Rivlin, Patricia K., Plaza, Stephen M.
The promise of extracting connectomes and performing useful analysis on large electron microscopy (EM) datasets has been an elusive dream for many years. Tracing in even the smallest portions of neuropil requires copious human annotation, the rate-li
Externí odkaz:
http://arxiv.org/abs/1508.06232
Autor:
Huang, Gary B., Plaza, Stephen
In this work, we propose a learning framework for identifying synapses using a deep and wide multi-scale recursive (DAWMR) network, previously considered in image segmentation applications. We apply this approach on electron microscopy data from inve
Externí odkaz:
http://arxiv.org/abs/1409.1789
Autor:
Plaza, Stephen M., Parag, Toufiq, Huang, Gary B., Olbris, Donald J., Saunders, Mathew A., Rivlin, Patricia K.
Reconstructing neuronal circuits at the level of synapses is a central problem in neuroscience and becoming a focus of the emerging field of connectomics. To date, electron microscopy (EM) is the most proven technique for identifying and quantifying
Externí odkaz:
http://arxiv.org/abs/1409.1801
For image recognition and labeling tasks, recent results suggest that machine learning methods that rely on manually specified feature representations may be outperformed by methods that automatically derive feature representations based on the data.
Externí odkaz:
http://arxiv.org/abs/1312.6159
Autor:
Huang, Gary B., Jain, Viren
Feedforward multilayer networks trained by supervised learning have recently demonstrated state of the art performance on image labeling problems such as boundary prediction and scene parsing. As even very low error rates can limit practical usage of
Externí odkaz:
http://arxiv.org/abs/1310.0354
We consider models for which it is important, early in processing, to estimate some variables with high precision, but perhaps at relatively low rates of recall. If some variables can be identified with near certainty, then they can be conditioned up
Externí odkaz:
http://arxiv.org/abs/0907.0418
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.