Abstract: In this presentation we build a multi-task deep learning model using DLPy to tag fashion clothing items. Convolutional neural networks show extraordinary performance for image classification and object recognition applications. DLPy is a high-level and easy-to-use Python API for SAS Deep Learning models. We explain how DLPy can be applied to data preparation, data processing, multi-task model building, assessment and deployment for image tagging.
Bio: Spiros Potamitis is a data scientist at SAS, a leading software and services provider in advanced analytics. Having acquired an MSc in Information Management from the University of Manchester, Spiros is specialising in the application and implementation of analytics to drive business outcomes. Prior of joining SAS, Spiros has acquired a wealth of predictive modelling experience while working in advanced analytics positions in Credit Risk, Customer Insights and CRM.