537
edits
Seminar on Internet Technologies (Winter 2020 2021): Difference between revisions
Seminar on Internet Technologies (Winter 2020 2021) (view source)
Revision as of 16:22, 2 February 2021
, 2 February 2021→Details
| (46 intermediate revisions by 7 users not shown) | |||
| Line 5: | Line 5: | ||
|credits=5 ECTS (BSc/MSc AI); 5 (ITIS) | |credits=5 ECTS (BSc/MSc AI); 5 (ITIS) | ||
|lecturer=[http://user.informatik.uni-goettingen.de/~fu Prof. Xiaoming Fu] | |lecturer=[http://user.informatik.uni-goettingen.de/~fu Prof. Xiaoming Fu] | ||
| | |ta =Tingting Yuan [tingting.yuan@cs.uni-goettingen.de], [http://www.net.informatik.uni-goettingen.de/people/shichang_ding Shichang Ding] and [http://www.net.informatik.uni-goettingen.de/people/sripriya%20srikant_adhatarao, Sripriya Srikant Adhatarao] | ||
|time=Nov 4th. Register on ecampus before Nov 8th.'''Please read this introduction slide | |time=Nov 4th. Register on ecampus before Nov 8th.'''Please read this introduction slide [https://docs.google.com/presentation/d/13hmKYBmB4tbTFNeK1GvBAs1qZntMYo75o8ycb1NgYXI/edit?usp=sharing]. If there is any question, please contact teaching assistants.''' | ||
|place=Through Zoom, waiting link | |place=Through Zoom, waiting link | ||
|univz=[https://univz.uni-goettingen.de/qisserver//rds?state=verpublish&status=init&vmfile=no&publishid=262017&moduleCall=webInfo&publishConfFile=webInfo&publishSubDir=veranstaltung] | |univz= [https://univz.uni-goettingen.de/qisserver//rds?state=verpublish&status=init&vmfile=no&publishid=262017&moduleCall=webInfo&publishConfFile=webInfo&publishSubDir=veranstaltung] | ||
}} | }} | ||
| Line 38: | Line 38: | ||
==Schedule== | ==Schedule== | ||
* '''7th Nov. 2020 ''': Deadline for registration the course | |||
* ''' | * '''20th Jan. 2021 ''': Deadline for registration to attend the final presentation | ||
* '''Jan. | * '''28th Jan. 2021 (14:00-18:00)''' : Final Presentations online (waiting for the link) | ||
* ''' | * '''28th March 2021 (23:59) ''': Deadline for submission of the report (should be sent to the topic adviser!). | ||
== Topics == | == Topics == | ||
| Line 53: | Line 53: | ||
|{{Hl2}} |'''Readings''' | |{{Hl2}} |'''Readings''' | ||
|{{Hl2}} |'''Available''' | |{{Hl2}} |'''Available''' | ||
|- | |- | ||
| Physics-informed neural networks: Principles, Case studies, and Prospects | | Physics-informed neural networks: Principles, Case studies, and Prospects | ||
| Line 67: | Line 60: | ||
using neural networks in the research field of Physics is nowadays more | using neural networks in the research field of Physics is nowadays more | ||
and more significant. The student is expected to be interested in the | and more significant. The student is expected to be interested in the | ||
interdisciplinary subject of physics and computer science. | the interdisciplinary subject of physics and computer science. | ||
| Basic programming knowledge, Basic machine learning knowledge | | Basic programming knowledge, Basic machine learning knowledge | ||
| [Yunxiao Zhang, yunxiao.zhang@ds.mpg.de] | | [Yunxiao Zhang, yunxiao.zhang@ds.mpg.de] | ||
| Line 73: | Line 66: | ||
| Yes | | Yes | ||
|- | |- | ||
| Comparative study of video analytic platforms and algorithms using neural networks: Principles, Standard Algorithms, and Open issues | |Comparative study of video analytic platforms and algorithms using neural networks: Principles, Standard Algorithms, and Open issues | ||
| In this topic, you will study and analyze the existing video analysis platforms and standard machine learning and deep learning algorithms with small set of experiment data, especially the data from sensor networks. The student is expected to have prior knowledge/experience in data science and programming skills. | | In this topic, you will study and analyze the existing video analysis platforms and standard machine learning and deep learning algorithms with small set of experiment data, especially the data from sensor networks. The student is expected to have prior knowledge/experience in data science and programming skills. | ||
| Basic programming knowledge, Basic machine learning knowledge | | Basic programming knowledge, Basic machine learning knowledge | ||
| [http://www.net.informatik.uni-goettingen.de/?q=people/sripriya-srikant-adhatarao Sripriya Adhatarao] | | [http://www.net.informatik.uni-goettingen.de/?q=people/sripriya-srikant-adhatarao Sripriya Adhatarao] | ||
| | | | ||
| | | No | ||
|- | |||
| Graph neural network | |||
| In this topic, you will study graph neural networks (GNNs), which are connectionist models that capture the dependence of graphs via message passing between the nodes of graphs. | |||
| Basic programming knowledge, Basic machine learning knowledge | |||
| [Tingting Yuan, tingt.yuan@hotmail.com] | |||
|[https://arxiv.org/pdf/1812.08434.pdf?source=post_page] | |||
| No | |||
|- | |- | ||
| | |AI painter | ||
| In this topic, you will study | | In this topic, you will study how AI has been used for painting. | ||
| Basic programming knowledge, Basic machine learning knowledge | | Basic programming knowledge, Basic machine learning knowledge | ||
| [Tingting Yuan, tingt.yuan@hotmail.com] | | [Tingting Yuan, tingt.yuan@hotmail.com] | ||
|[https:// | |[https://topten.ai/ai-painting-generators/] | ||
| | | No | ||
|- | |- | ||
| The maximum throughput problem in quantum entangle routing | | The maximum throughput problem in quantum entangle routing | ||
| In this topic, you will study entanglement routing problem in quantum network, which is a novel network built on quantum mechanics. | | In this topic, you will study the entanglement routing problem in a quantum network, which is a novel network built on quantum mechanics. | ||
| Basic programming knowledge, Basic mathematical programming knowledge | | Basic programming knowledge, Basic mathematical programming knowledge | ||
| [Bangbang Ren, bangbang.ren@cs.uni-goettingen.de] | | [Bangbang Ren, bangbang.ren@cs.uni-goettingen.de] | ||
|[https://dl.acm.org/doi/10.1145/3387514.3405853] | |[https://dl.acm.org/doi/10.1145/3387514.3405853] | ||
| Yes | | Yes | ||
|- | |||
| Video Analytics | |||
| Artificial Intelligence has been and is going to be popular for many years. Static object detection, recognition technique has been studied for many years. However, how these techniques work in a dynamic environment (eg. Self-driving ) is not clear. In this topic, we want to reveal which kind of technique performs better in a video surveillance system with limited computing and network resources. Based on this, our goal is to develop a real Wireless Moving Video Surveillance System which including video analysis, wireless data delivery, and data compression and fusion. Fortunately, we already have some preliminary work. | |||
| Interested in this topic, willing to follow the advisor's guidance, patience and time for reading multiple papers. Interested in embedded development, we will use Raspberry Pi and NVIDIA Jetson Nano Developer Kit. Have Fun With This Project! | |||
| [Weijun Wang, weijun.wang@informatik.uni-goettingen.de] | |||
| [https://www.microsoft.com/en-us/research/wp-content/uploads/2017/08/Bahl-MobiCom-2015.pdf] | |||
| Yes | |||
|- | |||
| Data augmentation with generative adversarial network (GAN) | |||
| Image classification datasets are often imbalanced, characteristic that negatively affects the accuracy of deep-learning classifiers. In this topic, you will learn to use GAN as an augmentation tool to restore balance in imbalanced datasets. This is challenging because the few minority-class images may not be enough to train a GAN. | |||
| Familiar with machine learning and deep learning; image processing with using python; | |||
| [Yachao Shao, yachao.shao@cs.uni-goettingen.de] | |||
| [https://arxiv.org/abs/1803.09655] | |||
| Yes | |||
|- | |||
| Passenger flow prediction with machine learning | |||
| You will study existing methods and algorithms used for the prediction of passenger flow in an urban area to determine the demand for buses, trams or trains. | |||
| Basic machine learning knowledge | |||
| [Fabian Wölk, fabian.woelk@cs.uni-goettingen.de] | |||
| | |||
| No | |||
|- | |||
| Optimization of public transport schedules | |||
| You will study techniques and algorithms to optimize the schedules for public transport systems. | |||
| Basic machine learning knowledge, Basic mathematical knowledge (knowledge in mathematical optimization problems can be helpful, but is not mandatory) | |||
| [Fabian Wölk, fabian.woelk@cs.uni-goettingen.de] | |||
| | |||
| No | |||
|- | |||
| Automatic Classification of Time Series (ACTS) | |||
| In this project you will apply machine learning techniques to identify differences and similarities in the evolution of real-world phenomena across different regions and countries, like the spread of the SARS-CoV2 virus. The student is expected to have prior knowledge in data science and programming skills. | |||
| Basic programming knowledge, basic machine learning knowledge | |||
| Pablo Gutierrez-Marques p.gutierrezmarques01@stud.uni-goettingen.de | |||
| [https://doi.org/10.1080/014311600210308] [https://doi.org/10.1109/ICDE.2017.68] | |||
| No | |||
|- | |- | ||
|} | |} | ||
| Line 113: | Line 148: | ||
* Based on the research, you should have your own ideas on your topic. | * Based on the research, you should have your own ideas on your topic. | ||
=== 4. Prepare | === 4. Prepare presentation === | ||
* Present on your topic to the audience (in English). | * Present on your topic to the audience (in English). | ||
| Line 130: | Line 165: | ||
Don't forget a summary of the topic and your ideas. | Don't forget a summary of the topic and your ideas. | ||
=== 5. Write | === 5. Write a report === | ||
* Present the problem with its background. | * Present the problem with its background. | ||
| Line 138: | Line 173: | ||
The report must be written in English according to common guidelines for scientific papers, between 12 and 15 pages of content (excluding the table of content, bibliography, etc.). | The report must be written in English according to common guidelines for scientific papers, between 12 and 15 pages of content (excluding the table of content, bibliography, etc.). | ||
Please note that you can not directly copy content from papers or webpages, as this will be considered plagiarism. All quoted images and tables need to indicate their source. | |||
=== 6. Course schedule=== | === 6. Course schedule=== | ||