Hour Group Inc.

Published purpose

To expand or work to integrate Deep Neural Network based matching algorithm into our search and matching tools (Deep Neural Networks (DNN have an input layer, an output layer and at least one hidden layer in between. Each layer performs specific types of sorting and ordering in a process that some refer to as “feature hierarchy.” Extracted features such as keywords, n-grams, TF/IDF, LSI etc. from target training job/resume, will be our input layers. Through DNN training, we will have refined output layer which is the result of initial input layer and several hidden layers generated by DNN. In the second step this output result will be decoded by applied to our target testing resume.) .