A ResNet Convolutional Neural Network for Time Series data using InceptionNet paradigms
The recent progress in Convolutional Neural Network (CNN) designs has extended their effectiveness to time series data as well. Time series features, which can be represented as one-dimensional vectors, open the door for training deeper networks using ResNet-inspired structures. Inception modules provide the capability to the network to handle objects and patterns of different sizes and capture both local details and global context. We propose an Inception-Residual CNN model tailored for time series data which will be applied on real-life data in retail.
ABOUT THE PRESENTER:
After graduating from the Faculty of Computer and Information Science at the University of Ljubljana in 2015, Vanja Mileski started working at the Jožef Stefan Institute (JSI). He was a Master’s student at the International Postgraduate School Jožef Stefan and a student researcher at the JSI. After finishing his Master’s studies, he applied his knowledge of data mining in the private sector as a Data Scientist in the retail, telecommunications, banking, stock market and insurance sectors.
His current research interests include time-series classification, deep learning, ResNet and Inception architectures.