Juan C. Caicedo (@jccaicedo) 's Twitter Profile
Juan C. Caicedo

@jccaicedo

Schmidt Fellow at the Broad Institute of MIT and Harvard

ID: 69134120

calendar_today26-08-2009 23:37:05

447 Tweet

358 Followers

146 Following

Anne Carpenter, PhD (@drannecarpenter) 's Twitter Profile Photo

We evaluated a couple of deep learning architectures vs. classical image processing on 20,000 manually annotated nuclei! Paper from Juan C. Caicedo in BioRxiv! biorxiv.org/content/early/…

Conrad Hackett (@conradhackett) 's Twitter Profile Photo

% who say religion is very important China 3% UK 10% Japan 10% Sweden 10% France 11% Russia 16% Australia 18% Spain 22% Canada 27% Mexico 45% US 53% Greece 56% Turkey 68% Brazil 72% Egypt 72% S Africa 75% India 80% Nigeria 88% Honduras 90% Indonesia 93% Ethiopia 98% #isa18wcs

% who say religion is very important
China 3%
UK 10%
Japan 10%
Sweden 10%
France 11%
Russia 16%
Australia 18%
Spain 22%
Canada 27%
Mexico 45%
US 53%
Greece 56%
Turkey 68%
Brazil 72%
Egypt 72%
S Africa 75%
India 80%
Nigeria 88%
Honduras 90%
Indonesia 93%
Ethiopia 98% 
#isa18wcs
Henning Koch (@triskweline) 's Twitter Profile Photo

(Using email) You have one inbox. (Sign up for Slack) You have 30 inboxes. (Slack adds threads feature) Your inboxes have inboxes.

Google DeepMind (@googledeepmind) 's Twitter Profile Photo

Using auxiliary tasks is a common way to speed up learning, though it's not clear a priori if/when a given aux task will help the main task. We propose a simple method that adapts aux losses using cosine similarity of gradients: arxiv.org/abs/1812.02224 Balaji Lakshminarayanan @rpascanu Sid Jayakumar

Anne Carpenter, PhD (@drannecarpenter) 's Twitter Profile Photo

Teachers! Parents! It is legal and perfectly welcome to email scientists asking for a PDF of their paper. Until all papers are free, please RT to make this more widely known. And fyi, scientists don't get the $$ from sales of papers so all it costs us is 1 minute of time!

Shantanu Singh (@shantanuxsingh) 's Twitter Profile Photo

What are the actively-maintained resources for hosting deep learning models (model zoos) out there? We found some; what else exists? Genomics kipoi.org Detection(TF) github.com/tensorflow/mod… Generic(MXNet) mxnet.incubator.apache.org/model_zoo/inde… Generic modelzoo.co

Beth Cimini 🔬💻 📊 (@bosoxbiobeth) 's Twitter Profile Photo

The Carpenter Lab at the Broad Institute (Cambridge, MA, US) is hiring for our new Postdoctoral Training Program in Bioimage Analysis. We are looking for bright, organized biological microscopists who want to learn to collaboratively create cutting-edge image analysis workflows.

Shantanu Singh (@shantanuxsingh) 's Twitter Profile Photo

Want to devote your expertise in machine learning to accelerate the pace at which new medicines are found? Join Anne Carpenter, PhD and me at the Broad Institute to glean insights from biological images! Learn more about this postdoctoral position at broad.io/mlcbpostdoc.

Juan C. Caicedo (@jccaicedo) 's Twitter Profile Photo

Machine learning and computer vision postdoc position in my new group at the Broad Institute! Please apply / RT broadinstitute.wd1.myworkdayjobs.com/broad_institut…

Nature Methods (@naturemethods) 's Twitter Profile Photo

Check out the results of the 2018 Data Science Bowl and learn about automated segmentation of cell nuclei! nature.com/articles/s4159…

Check out the results of the 2018 Data Science Bowl and learn about automated segmentation of cell nuclei! nature.com/articles/s4159…
CytoData Society (@cytodata) 's Twitter Profile Photo

Join the morning session of the Cytodata #symposium on October 18 and learn about #interpretability of #DeepLearning models in #bioimage, deep learning applications to organelle tracking and methods to understand heterogeneity from #SingleCell #data! secure2.convio.net/allins/site/Ca…

Join the morning session of the Cytodata #symposium on October 18 and learn about #interpretability of #DeepLearning models in #bioimage, deep learning applications to organelle tracking and methods to understand heterogeneity from #SingleCell #data!
secure2.convio.net/allins/site/Ca…
Anne Carpenter, PhD (@drannecarpenter) 's Twitter Profile Photo

Neat trick to train deep learning models without conventional biological ground truth: Weakly supervised learning of single-cell feature embeddings. Postdoc Juan C. Caicedo's paper coming out at CVPR: biorxiv.org/content/early/…

Neat trick to train deep learning models without conventional biological ground truth: Weakly supervised learning of single-cell feature embeddings. Postdoc <a href="/jccaicedo/">Juan C. Caicedo</a>'s paper coming out at CVPR: biorxiv.org/content/early/…