Vanja MILESKI: Deep learning for time series data using Inception and ResNet paradigms

V ponedeljek, 16. maja 2022, bo ob 16.00 uri prek spletnih orodij na daljavo izvedeno
predavanje v okviru PONEDELJKOVEGA SEMINARJA RAČUNALNIŠTVA IN INFORMATIKE
Oddelkov za Informacijske znanosti in tehnologije UP FAMNIT in UP IAM.

ČAS/PROSTOR: 16. maj 2022 ob 16.00 na daljavo

—————————————–
PREDAVATELJ: Vanja MILESKI
—————————————–

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.

—————————————————————————————————————-
NASLOV: Deep learning for time series data using Inception and ResNet paradigms
—————————————————————————————————————-

POVZETEK:

With the advancements in Convolutional Neural Network (CNN) architectures such as Inception modules and ResNet architectures, it is of particular interest to study these advances and apply them on time series data. Time series features can be viewed as one-dimensional vectors, on which we can apply different types of filters using Inception modules, and then train a deeper network using a ResNet-like architecture. We propose an idea of combining these advancements and testing them on real-life data of customer shopping habits obtained from a large retailer in Slovenia with the hopes of beating traditional ML techniques.

—————————————————————————————————

Seminar bo potekal v angleškem jeziku v Zoom “klepetalnici” na naslovu:

https://upr-si.zoom.us/j/297328207?pwd=S3Zpdk1VR3pjckNtWkQwKzlvcDR5UT09

Vabljeni!