CVML Web lectures 3rd June 2020: 1) Deep Learning. Convolutional Neural Networks 2) Deep Object Detection

Εκ μέρους του καθηγ. κ. Ι. Πήτα σας ενημερώνουμε για το παρακάτω:

 

Dear Computer Vision/Machine Learning/Autonomous Systems students,  engineers, scientists and enthusiasts,

Artificial Intelligence and Information analysis (AIIA) Lab, Aristotle University of Thessaloniki, Greece is proud to have launched the live CVML Web lecture series

that covers very important Computer Vision/Machine Learning topics. Two new upcoming 45 min lectures will take place soon:

1) Deep Learning. Convolutional Neural Networks

2) Deep Object Detection

Date/time: Wednesday 3rd June 2020,  17:00-18:30 EEST for both lectures (7:00-8:30 am California time, 10:00-11:30 am New York time, 22:00-23:30 Beijing time).

Registration  can be done using the link: http://icarus.csd.auth.gr/cvml-web-lecture-series/

Registration for asynchronous access to CVML live Web lecture material (video, pdf/ppt) for any past/present lecture can be done using the link: http://icarus.csd.auth.gr/cvml-web-lecture-series/

Lecture abstracts

1) Deep Learning. Convolutional Neural Networks, Wednesday 3rd June 2020, 17:00-17:45 EEST

Summary: Introduction to deep learning, focusing on convolutional neural networks (CNNs). From multilayer perceptrons to deep architectures. Fully connected layers. Convolutional layers. Tensors and mathematical CNN formulations. Pooling. Training convolutional NNs. Initialization. Batch Normalization, Data augmentation. Regularization. Dropout. AlexNet, ZFNet, ResNet, SqueezeNet, Inception, GoogleLeNet, Network-In-Network architectures. Lightweight deep learning.  Deployment on embedded systems. Performance metrics.

2) Deep Object Detection,  Wednesday 3rd June 2020, 17:45-18:30 EEST
Summary: An overview is provided on target detection using deep neural networks. Detection as classification and regression task, Modern architectures for target detection: RCNN, Faster RCNN, R-FCN, YOLO v1/2/3/4, SSD Lightweight detector architectures. Object detection performance metrics. Evaluation and benchmarking. Deployment in embedded platforms.Recently, Convolutional Neural Networks (CNNs) have been used for the task of object detection with great results. However, using such models on drones for real-time face detection is prohibited by the hardware constraints that drones impose. Various architectures and settings are examined to facilitate the use of CNN-based object detectors on a drone with limited computational capabilities.

Lecturer: Prof. Ioannis Pitas (IEEE fellow, IEEE Distinguished Lecturer, EURASIP fellow) received the Diploma and PhD degree in Electrical Engineering, both from the Aristotle University of Thessaloniki, Greece. Since 1994, he has been a Professor at the Department of Informatics of the same University. His current interests are in the areas of machine learning, computer vision, intelligent digital media, human centered interfaces, affective computing, 3D imaging and biomedical imaging. He has published over 860 papers, contributed in 44 books in his areas of interest and edited or (co-)authored another 11 books. He has also been member of the program committee of many scientific conferences and workshops. In the past he served as Associate Editor or co-Editor of 9 international journals and General or Technical Chair of 4 international conferences. He participated in 69 R&D projects, primarily funded by the European Union and is/was principal investigator/researcher in 41 such projects. He has 31000+ citations to his work and h-index 83+ (Google Scholar). Prof. Pitas lead the big European H2020 R&D project MULTIDRONE: https://multidrone.eu/ and is principal investigator (AUTH)  in H2020 projects Aerial Core and AI4Media. He is chair of the Autonomous Systems initiative https://ieeeasi.signalprocessingsociety.org/.

Lecturing record of Prof. I. Pitas: He was Visiting/Adjunct/Honorary Professor/Researcher and lectured at several Universities: University of Toronto (Canada), University of British Columbia (Canada), EPFL (Switzerland), Chinese Academy of Sciences (China),  University of Bristol (UK), Tampere University of Technology (Finland), Yonsei University (Korea), Erlangen-Nurnberg University (Germany), National University of Malaysia, Henan University (China). He delivered 90 invited/keynote lectures in prestigious international Conferences and top Universities worldwide. He run 17 short courses and tutorials on Autonomous Systems, Computer Vision and Machine Learning, most of them in the past 3 years in many countries, e.g., USA, UK, Italy, Finland, Greece, Australia, N. Zealand, Korea, Taiwan, Sri Lanka, Bhutan.

Relevant links: a) Prof. I. Pitas: https://scholar.google.gr/citations?user=lWmGADwAAAAJ&hl=el  b) AIIA Lab www.aiia.csd.auth.gr

General information: Lectures will consist primarily of live lecture streaming and PPT slides. Attendees (registrants) need no special computer equipment for attending the lecture. They will receive the lecture PDF before each lecture and will have the ability to ask questions real-time. Audience should have basic University-level undergraduate knowledge of any science or engineering department (calculus, probabilities, programming, that are typical e.g., in any ECE, CS, EE undergraduate program).  More advanced  knowledge (signals and systems, optimization theory, machine learning) is very helpful but nor required.

These two lectures are part of a 15 lecture CVML web course ‘Computer vision and machine learning for autonomous systems’ (April-June 2020):

Introduction to autonomous systems                                                               (delivered 25th April 2020)

Introduction to computer vision                                                                        (delivered 25th April 2020)

Image acquisition, camera geometry                                                                (delivered   2nd May 2020)

Stereo and Multiview imaging                                                                            (delivered   2nd  May 2020)

Structure from Motion                                                                                         (delivered   9th May 2020)

2D convolution and correlation algorithms                                                      (delivered   9th May 2020)

Motion estimation                                                                                                (delivered   20th May 2020)

Introduction to Machine Learning                                                                     (delivered   20th May 2020)

Artificial Neural Networks. Perceptron                                                         (delivered   27th May 2020)

Multilayer perceptron. Backpropagation                                                      (delivered   27th May 2020)

Deep learning. Convolutional NNs

Deep object detection

Object tracking

Localization and mapping

Fast convolution algorithms. CVML programming tools.

Sincerely yours

Prof. Ioannis Pitas

Director of Artificial Intelligence and Information analysis (AIIA) Lab, Aristotle University of Thessaloniki, Greece

Post scriptum: To stay current on CVMl matters, you may want to register to the CVML email list, following instructions in https://lists.auth.gr/sympa/info/cvml