Faculty of Technical Sciences

Subject: Deep Learning for Autonomous and Networked Vehicles (17.CEM822)

General information:
 
Category Professional-applicative
Scientific or art field Computer Engineering and Computer Communication
ECTS 6

Introduce theoretical principles, practical aspects and advanced techniques for deep learning and artificial intelligence in autonomous and networked vehicles applications.

The students will gain detailed knowledge about fundamentals, practical and implementation aspects of deep learning and neural networks,. The will learn about applications specific to autonomous and networked vehicles.

Deep learning belongs to the field of artificial intelligence and machine learning,Image classification, speech recognition, language translation, medical diagnostics, robot and vehicle control are limited applications of deep learning. In this course we will cover the following topics. - Introduction to machine learning and relationship to deep learning. - The neural network architectures: feed-forward, convolutional, and recurrent. - Learning and adaptation - with or without supervision, back-propagation, training, validation... - Hyper-parameter optimization - Reinforcement-learning - Vehicular applications, case studies (YOLO algorithm, NVIDIA,...) In addition to lectures, there is a hands-on lab work using the existing training data sets, Tensor Flow a,d the ALPHA board that integrates TI System-on-Chip. As an alternative a GPU NVIDIA platform will be considered.

Lectures, case-study analysis, lab work, practical project assignment and lab work.

Authors Title Year Publisher Language
Lex Fridman Deep Learning for Self-Driving Cars, MIT 2017 MIT English
Zoran Kostic ECBM E4040 Neural Networks and Deep Learning, Columbia University, 2017 2017 English
Fei-Fei Li CS231n Convolutional Neural Networks for Visual Recognition, Stanford University, Spring 2017 2017 English
Goodfellow, I., Bengio, Y., Courville, A. Deep Learning 2017 MIT Press, Cambridge English
Course activity Pre-examination Obligations Number of points
Project defence Yes Yes 50.00
Written part of the exam - tasks and theory No Yes 50.00

Assoc. Prof. Lukač Željko

Associate Professor

Lectures

Assoc. Prof. Lukač Željko

Associate Professor

Computational classes
API Image

Asistent sa doktoratom dr Milošević Milena

Assistant with PhD

Computational classes

Faculty of Technical Sciences

© 2024. Faculty of Technical Sciences.

Contact:

Address: Trg Dositeja Obradovića 6, 21102 Novi Sad

Phone:  (+381) 21 450 810
(+381) 21 6350 413

Fax : (+381) 21 458 133
Emejl: ftndean@uns.ac.rs

© 2024. Faculty of Technical Sciences.