Classification and automatic recognition of objects using H2o package

Deep learning (DL) is a process that consists of a set of methods which classifies the raw data to meaningful information that fed into the machine. Deep Convolutional nets composed of various processing layers to learn and represent the data. It has multiple levels of abstraction to process images, video, speech and audio. H2o deep learning architecture has many features that include supervised training protocol, memory efficient Java implementation, adaptive learning, and with related CRAN packages. H2o uses supervised training protocol with a uniform adaptive option which is an optimization based on the size of the network. It can take clusters of computing nodes to train on the entire data set but automatically shuffling the training examples for each iteration locally. The framework supports regularization techniques to prevent overfitting. Further, H2o R has intuitive web interface using localhost and IP address. In this research the computations are performed in the H2o cluster and initiated by REST calls (in highly optimized Java code) from R. Since SPARK is available in R, H2o uses a single R session to communicate H2o Java cluster via REST calls. H2o runs inside the Spark executor JVM. Using these packages in R, we demonstrate the classification and automatic recognition of objects. The research extends the NOAA VIIRS Night fires data to detect the persistent fire activity at a given location around the globe. To perform the classification, we use the H2o deep learning package in R Language.