Learn More
Detecting and reading text from natural images is a hard computer vision task that is central to a variety of emerging applications. Related problems like document character recognition have been widely studied by computer vision and machine learning researchers and are virtually solved for practical applications like reading handwritten digits. Reliably(More)
Full end-to-end text recognition in natural images is a challenging problem that has received much attention recently. Traditional systems in this area have relied on elaborate models incorporating carefully handengineered features or large amounts of prior knowledge. In this paper, we take a different route and combine the representational power of large,(More)
MicroRNAs (miRNA) are approximately 21 nucleotide-long non-coding small RNAs, which function as post-transcriptional regulators in eukaryotes. miRNAs play essential roles in regulating plant growth and development. In recent years, research into the mechanism and consequences of miRNA action has made great progress. With whole genome sequence available in(More)
Scaling up deep learning algorithms has been shown to lead to increased performance in benchmark tasks and to enable discovery of complex high-level features. Recent efforts to train extremely large networks (with over 1 billion parameters) have relied on cloudlike computing infrastructure and thousands of CPU cores. In this paper, we present technical(More)
Breast milk is a complex liquid rich in immunological components that affect the development of the infant's immune system. Exosomes are membranous vesicles of endocytic origin that are found in various body fluids and that can mediate intercellular communication. MicroRNAs (miRNAs), a well-defined group of non-coding small RNAs, are packaged inside(More)
Familial idiopathic basal ganglia calcification (IBGC) is a genetic condition with a wide spectrum of neuropsychiatric symptoms, including parkinsonism and dementia. Here, we identified mutations in SLC20A2, encoding the type III sodium-dependent phosphate transporter 2 (PiT2), in IBGC-affected families of varied ancestry, and we observed significantly(More)
Reading text from photographs is a challenging problem that has received a significant amount of attention. Two key components of most systems are (i) text detection from images and (ii) character recognition, and many recent methods have been proposed to design better feature representations and models for both. In this paper, we apply methods recently(More)
In the adult heart, a variety of stresses induce re-expression of a fetal gene program in association with myocyte hypertrophy and heart failure. Here we show that histone deacetylase-2 (Hdac2) regulates expression of many fetal cardiac isoforms. Hdac2 deficiency or chemical histone deacetylase (HDAC) inhibition prevented the re-expression of fetal genes(More)
We present an efficient "sparse sampling" technique for approximating Bayes optimal decision making in reinforcement learning, addressing the well known exploration versus exploitation tradeoff. Our approach combines sparse sampling with Bayesian exploration to achieve improved decision making while controlling computational cost. The idea is to grow a(More)
Numerous groups have applied a variety of deep learning techniques to computer vision problems in highway perception scenarios. In this paper, we presented a number of empirical evaluations of recent deep learning advances. Computer vision, combined with deep learning, has the potential to bring about a relatively inexpensive, robust solution to autonomous(More)