APPARATUS FOR DATA CLASSIFICATION BASED ON BOOST POOLING NEURAL NETWORK AND METHOD FOR TRAINING THE APPATRATUS

摘要

An apparatus for classifying data based on a boost pooling neural network is disclosed. According to an embodiment, the data classification apparatus includes an input layer to which data is input, an output layer that outputs a plurality of first output values for data with respect to at least some classes and one first output value for the remaining classes; It may include a neural network including a boost pooling layer that outputs one second output value for each class as an input of one or more first output values output for each class.