Summer semester 2021
Overview
The Summer Semester 2021 during COVID-19
Due to the current situation regarding the Coronavirus all teaching courses will be held digitally. If you want to participate in a specific course, please follow the corresponding instructions under that course on this webpage.
We offer in the summer semester 2021 the following courses:
- Programmieren in C (Bachelor, German)
- Internet of Things: Protocols and System Software (Master, English)
- Project: Embedded Systems (Bachelor/Master, German/English)
- Seminar: Implementation and Optmisation of Deep Learning Algorithms (Bachelor/Master, German/English)
Lecture with exercise for Bachelor AIProgrammieren mit C
| Lecturer: | Prof. Dr. Gregor Schiele (Lecture) Lukas Einhaus (Exercise) |
| Language: | German |
| Turnus: | Summer semester |
| Time: | Wednesday, 10:00 am -12:00 pm (Lecture) Tuesday, 12:00 pm - 2:00 pm (Exercise) |
| Place: | Online (Zoom and Youtube) |
| Begin: | 14.04.2021 |
This bachelor lecture teaches the basics of Programming in the programming language C. Complementary it will give a short prospect onto the programming language C++, which is based on C. Despite its long history C remains to be one of the most widspread and important programming languages ever, especially when doing system level programming. It is easy to learn, but hard to master, as it only has a small number of keywords and concepts, that allow to emulate many modern programming techniques.
In detail the following topics will be covered: General Concepts of programming languages, variables and types in C, operators and expressions, control structures and functions, the preprocessor, pointers, static and dynamic memory management, error handling, bit manipulation, modules and abstract data types, unit tests and test driven development in C, object orientation in C++.
The lecture builds up on the lectures "Grundlegende Programmiertechniken" and "Fortgeschrittene Programmiertechniken", i.e. basic programming skills (types and variables, loops, subroutines and recursion) and basic knowledge about data structures and algorithms is required.
Digital Course:
This course will only be offered digitally, through videos and live streams. To participate in this couse, please enroll into the corresponding Moodle-Course. To enroll in the Moodle-Course this semester you do not need a password. In the course you will find all necessary informations to be able to participate in the first session.
Lecture with exercise for Master AI / Master ISEInternet of Things: Protocols and System Software
| Lecturer: | Prof. Dr. Gregor Schiele (Lecture) Chao Qian (Exercise) |
| Language: | English |
| Turnus: | Summer semester |
| Time: | Tuesday, 4:00 pm - 6:00 pm (Lecture) Wednesday, 2:00 pm - 4:00 pm (Exercise) |
| Place: | Online (Zoom and Youtube) |
| Begin: | 13.04.2021 |
This masters lecture will introduce the research area of the "Internet of Things" (IoT), where billions of embedded systems (actuator, sensors) make continously data in real time to about the real world available to the Internet. Topics, that will be covered are:
Hardware plattforms (e.g. SBCs, Sensor nodes), communication protocols (e.g. IEEE 802.15.4, 6LoWPAN, CoAP, MQTT), data modelling (e.g. linked data, RDF, SSN), data management and access (e.g. SPARQL, continous queries with CQELS, "Big Data"), system software and software plattforms (e.g. Eclipse Ponte, Xively, BASE, PCOM), future work ("programmable world"). An exercise will complement the theoretical knowledge with practical task of programming IoT-Systems, e.g. with Arduinos or Raspberry Pis.
Digital Course:
This course will only be offered digitally, through videos and live streams. To participate in this couse, please enroll into the corresponding Moodle-Course. To enroll in the Moodle-Course this semester you do not need a password. In the course you will find all necessary informations to be able to participate in the first session.
ProjectProject: “Embedded Systems”
| Lecturer: | Prof. Dr. Gregor Schiele Lukas Einhaus Chao Qian |
| Language: | German/English |
| Turnus: | Summer Semester |
| Time: | Wednesday, 2:00 pm - 4:00 pm (Kickoff) |
| Place: | Online |
| Begin: | 14.04.2021 |
You are a member of an IoT development team at a small IT consulting company. One of your customers asked you to help with developing their new product. For that they want to explore the potential of two core IoT technologies: First, they want to get more experience on how to connect their devices with each other, with smart phones and with the Internet. For that they want you to demonstrate how well different wireless communication standards would work, namely WLAN (802.11), ESP-Mesh, Bluetooth Mesh, Bluetooth and Bluetooth LE. Second, they want to know how to use machine learning on their embedded device directly, instead of in the Cloud. For that they want you to evaluate TensorFlow Lite and TensorFlow Lite for Microcontrollers to implement an image processing system that detects humans in a video feed that is recorded on the embedded devices.
Your job as a team is to demonstrate these technologies to your customer and to characterize to him how they perform, what is doable, what are weaknesses, etc. You will be using the ESP32 platform for that and will present your results in multiple intermediary presentations. Each one of you will receive multiple development boards for your experiments.
Prerequisites: Good knowledge of Python and C is mandatory. Additionally we recommend you have experience in at least one of the following: machine learning, image processing, embedded programming with C, FreeRTOS, wireless communication
Digital Course:
This course will only be offered digitally, through videos and live streams. To participate in this couse, please enroll into the corresponding Moodle-Course. To enroll in the Moodle-Course this semester you do not need a password. In the course you will find all necessary informations to be able to participate in the first session.
Bachelor- and MasterseminarSeminar: Implementation and Optmisation of Deep Learning Algorithm
| Lecturer: | Prof. Dr. Gregor Schiele Christopher Cichiwskyj Christopher Ringhofer Lukas Einhaus Chao Qian |
| Language: | German/English |
| Turnus: | Summer Semester |
| Time: | Thu, 11:00-13:00h |
| Place: | Online |
| Begin: | Thu, 15.04.2021, 11:00h (Kickoff) |
This seminar will focus on techniques to optimise deep learning algorithms for execution on embedded MCUs and FPGAs. The following topics will be offered:
- MobileNets v1, v2
- MobileNets v3, EfficientNet
- SqueezeNet
- Structured Pruning for Deep Convolutional Neural Networks
- Quantization-Guided Training
- Realizing Binary Neural Networks with XNOR-Popcount
- LogicNets: Co-Designed Neural Networks and Circuits for Extreme-Throughput Applications
- Learning FPGA Configurations for highly efficient neural network inference
- MCUNet: Tiny Deep-Learning on IoT Devices
- FPGA Implementation-aware Neural Architecture Search
- Configurable N-fold Hardware Architecture for Convolutional Neural Networks
- Energy- and time-efficient matrix multiplication on FPGAs
Digital Course:
This course will only be offered digitally, through videos and live streams. To participate in this couse, please enroll into the corresponding Moodle-Course. To enroll in the Moodle-Course this semester you do not need a password. In the course you will find all necessary informations to be able to participate in the first session.