ResNet is a Deep Learning Network considered a reference for Image Classification. It is used in cases where a high classification accuracy is required. The innovative idea behind this network is the “Residual Skip Connections” that links the output of the current layer with that of a previous layer.
Temporal-ResNet (T-ResNet) is a state-of-the-art algorithm for Video Scene Classification: starting from the ResNet structure it adds Residual Connections between video frames. In this way it adds to the so-called “Spatial Awareness”, also a “Temporal Awareness”.
The goal of this thesis is to reimplement the original T-ResNet algorithm written in MATLAB, in TensorFlow and to apply it to specific datasets provided by Addfor S.p.A. and measure its performance.
It is required that the candidate has significant mathematical foundations, analytical skills and excellent programming skills, especially in Python.
The candidate will be supported by highly qualified personnel and, when necessary, he will be enabled to access the company computing resources
(IBM PowerAI equipped with NVIDIA P100 and V100 cards).
Who we’re looking for
Students that are about to get their master degree in: Computer Science, Mathematics, Physics
Skills: Python, C/C++, math, exp. w. at least one among TensorFlow / PyTorch / BigDL, excellent skills in mathematical analysis, ability to analyse and research scientific publications
Duration of this Projects: 6-8 months