Built with intelligent deep neural networks hosted all through the web, our process is streamlined to perform a multitude of tasks for governments to assist refugees.
Historical and government data is collected and processed on a python backend.
Data is fed to a triple ensamble deep convolutional network scheme each with specialized architectures for specific tasks.
Backend web and AI architecture interact efficiently with frontend for interpretation for government officials.
We leverage state-of-the-art research to train and implement effective and accurate deep learning solutions for refugees and government officials. The data files are collected from governments officials and quered to the web server. The processed data is simultaenously fed to each of the 3 networks in an ensamble scheme, and a variety of outputs are fed to the frontend. Below are details on the specific model architectures we implement from recent research. The figure below is a diagram of our triple neural network architecture.