Font Size

SCREEN

Cpanel

Predavanje "Deep Learning from Sequential Data", S. Vučetić

Vreme: sreda 17. maj 2017. u 17h.

Mesto: sala 313.

O predavanju:

In this talk we will discuss the state of the art approaches for descriptive and predictive analysis of sequential data, such as text and event logs. A critical challenge in the analysis of sequential data is data representation, which refers to converting the raw data into a form that is suitable for machine learning algorithms. Many machine learning algorithms, such as neural networks, require the input to be provided as a fixed-length vector and, for a long time, this has been considered a major obstacle for successful learning from sequential data. The recent progress in machine learning has resulted in several powerful ideas for better representation and learning from sequential data. Among those ideas, probably the most powerful are distributed representations and deep learning. We will describe the intuition behind these ideas and demonstrate their promise by showing our recent results on the analysis of micro-blogging data and medical records data.

O predavaču:

Slobodan Vucetic is an Associate Professor and Chair of the Department for Computer and Information Sciences at Temple University. He got his Ph.D. degree in Electrical Engineering from Washington State University in 2001, and his B.S. and M.S. degrees in Electrical Engineering are from the University of Novi Sad. His research expertise and interests are in machine learning, data science, and big data. His research focuses on solving real-life knowledge discovery problems through development of novel machine learning algorithms and is driven by open problems in a wide array of disciplines such as Public Health, Medicine, Biology, Geosciences, Education, Marketing, Social Sciences, Traffic Engineering, and Industrial Engineering. Dr. Vucetic has published over 100 research papers that have been cited over 5,000 times and his current research is funded by the U.S. National Science Foundation (NSF), the National Institutes or Health, and industry. He is a recipient of the NSF CAREER award.

Poseta studenata kompaniji Robert Bosch, Šimanovci​

Poseta studenata Odseka za signale i sisteme kompaniji Robert Bosch u Šimanovcima biće organizovana ​u petak 12. maja 2017.godine. Zainteresovani studenti se mogu prijaviti asistentu Nikoli Kneževiću (Ova adresa el. pošte je zaštićena od spambotova. Omogućite JavaScript da biste je videli.) sa Naslovom poruke "Ekskurzija u Bosch". Prevoz studenata je obezbedila kompanija Robert Bosch. Broj posetilaca je ograničen i prednost će dobiti studenti po vremenu prijave.

Internet of Things - radionica za studente

5.4.2017. godine u RC-u biće održana radionica za studente na temu Internet of Things (IoT). U okviru ove radionice studenti će naučiti kako se prave cele IoT aplikacije od hardvera, do pisanija u oblaku i analize podataka. Sudenti će imati na raspolaganju Adafruit Microsoft IoT Pack da prave projekte u toku radionice.

Neke od tehnologija o kojima će se učiti su: Raspberry Pi, Windows 10 IoT Core, C#, IoT Hub, Stream Analytics, Power Bi, Azure IoT Suite itd. Na kraju radionice studenti će znati da prave IoT aplikaciju pomoću Microsoft tehnologija, od nule do oblaka.

  • Web stranica za početak razvoja sa Windows 10 IOT
  • Instaliranje i proveravanje setiranje preduvjetima , Windows 10 developer mode, Visual Studio 10 etc.
  • Proveriti da li je instaliran Windows IoT Core alate i instalirati Windows IoT Core na SD karticu
  • Pokrenuti Raspberry PI
  • Priključivanje pomoću Remote PowerShell i promjena konfiguracije.
  • Spajanje s web portal i menjanje konfiguracije njime.
  • Kako kontrolirati jedan izlaz,  Blinky sample
  • Rasprava o ispravnom načinu komande izlazne linije.
  • Kako čitati ulaznu liniju, na temelju push button sample
  • Rasprava o analognih i digitalnih ulazninh podatka.
  • Što je IoT Hub? Napravite IoT Hub.
  • Rasprava o bezbednost IoT Hub -a.
  • Izmjena posljednjeg sample za spajane na IoT Hub.
  • Što je Stream Analytics? Koji jezik se to koristiti? Gdje mogu napisati rezultate?
  • Što učiniti s dobivenim podacima?
  • Slanje naredbi za uređaj
  • Stvaranje moćne vizualizacije podataka pomoću Power BI
  • Razgledate zapakirano  rješenje IOT Suite. Kreirati  i pokrenuti jedan IOT Suite.
  • Istražite mogućnosti upravljanja uređaja  s IOT Hub.

Za prisustvovanje ovoj radionici studenti treba da se prijave na mail svujnovic (at) etf.rs.

Research Associates (Postdocs) openings in Luxemburg

The Interdisciplinary Centre for Security, Reliability and Trust (SnT) invites applications from Research Associates/Postdocs in the area of MIMO Radar with a focus on automotive applications. The project spans theoretical research as well as a testbed activity. More information about the project can be obtained here.

PhD pozicija u Francuskoj

Otvorena je PhD pozicija u gradu Lille u Francuskoj za izradu disertacije pod naslovom Sequential Bayesian Inference Methods for Complex Dynamical Systems. Više informacija o konkursu može se dobiti ovde.

Prijavljivanje

Vi ste ovde: Home Obaveštenja