Generalizable adversarial training via spectral normalization
Deep neural networks (DNNs) have set benchmarks on a wide array of supervised learning
tasks. Trained DNNs, however, often lack robustness to minor adversarial perturbations to …
tasks. Trained DNNs, however, often lack robustness to minor adversarial perturbations to …
[HTML][HTML] Fast and accurate single-cell RNA-seq analysis by clustering of transcript-compatibility counts
Current approaches to single-cell transcriptomic analysis are computationally intensive and
require assay-specific modeling, which limits their scope and generality. We propose a …
require assay-specific modeling, which limits their scope and generality. We propose a …
[PDF][PDF] Valid post-clustering differential analysis for single-cell RNA-Seq
Single-cell computational pipelines involve two critical steps: organizing cells (clustering)
and identifying the markers driving this organization (differential expression analysis). State-of-…
and identifying the markers driving this organization (differential expression analysis). State-of-…
[HTML][HTML] An interpretable framework for clustering single-cell RNA-Seq datasets
Background With the recent proliferation of single-cell RNA-Seq experiments, several methods
have been developed for unsupervised analysis of the resulting datasets. These methods …
have been developed for unsupervised analysis of the resulting datasets. These methods …
A Fourier-based approach to generalization and optimization in deep learning
The success of deep neural networks stems from their ability to generalize well on real data;
however, et al. have observed that neural networks can easily overfit randomly-generated …
however, et al. have observed that neural networks can easily overfit randomly-generated …
Towards a Post-Clustering Test for Differential Expression.
Single-cell technologies have seen widespread adoption in recent years. The datasets
generated by these technologies provide information on up to millions or more individual cells; …
generated by these technologies provide information on up to millions or more individual cells; …
[PDF][PDF] Learning the language of the genome using RNNs
We explore how deep recurrent neural network (RNN) architectures can be used to capture
the structure within a genetic sequence. We first confirm that a characterlevel RNN can …
the structure within a genetic sequence. We first confirm that a characterlevel RNN can …
Eradication of large established tumors in mice by combination immunotherapy that engages innate and adaptive immune responses
…, JM Engreitz, RT Williams, K Rakhra, MH Zhang… - Nature medicine, 2016 - nature.com
Checkpoint blockade with antibodies specific for cytotoxic T lymphocyte–associated protein (CTLA)-4
or programmed cell death 1 (PDCD1; also known as PD-1) elicits durable tumor …
or programmed cell death 1 (PDCD1; also known as PD-1) elicits durable tumor …
[PDF][PDF] Likun Zhang, Ganesh Sankaranarayanan, Venkata Sreekanth Arikatla, Woojin Ahn, Cristol Grosdemouge, Jesse M. Rideout, et al.
S Trainer - academia.edu
Background Mastering laparoscopic surgical skills requires considerable time and effort.
The Virtual Basic Laparoscopic Skill Trainer (VBLaST-PT©) is being developed as a …
The Virtual Basic Laparoscopic Skill Trainer (VBLaST-PT©) is being developed as a …
A study of fast reactor fuel transmutation in a candidate dispersion fuel design
M DeHart, H Zhang, E Shaber, M Jesse - 2010 - osti.gov
Dispersion fuels represent a significant departure from typical ceramic fuels to address
swelling and radiation damage in high burnup fuel. Such fuels use a manufacturing process in …
swelling and radiation damage in high burnup fuel. Such fuels use a manufacturing process in …