Im folgenden finden Sie alle offenen studentischen Arbeiten unseres Lehrstuhls. Wir bieten Masterarbeiten, Bachelorarbeiten, Forschungspraxis, Ingeneurpraxis und interdisziplinäre Projekte an. Falls für Sie keine passende Arbeit angeboten wird, kontaktieren Sie bitte einen wissenschaftlichen Mitarbeiter. Über die Forschungsgebiete unseres Lehrstuhls können Sie sich unter Forschung informieren. Außerdem bieten wir Seminararbeiten in VLSI-Entwurfsverfahren (WS/SS) und EDA (WS) an.

Bachelorarbeiten

Implementation of a DXF library for microfluidics design software

Beschreibung

DXF is short for Drawing Exchange Format or Drawing Interchange Format and is a vector file type. Engineers, designers, and architects often use the DXF format for drawings during product design. DXF is widely used in industrial production. Many devices such as printers, laser cutters, CNC machining, etc. accept DXF format as input. In this project, we would like you to implement a generic DXF library that can be used by different software to produce designs in DXF format. 

Voraussetzungen

  • Knowledge and experience in web design and web development or desktop application development
  • Good understanding of JavaScript and PHP or Java Spring Boot or the wiliness to learn them
  • Basic knowledge of Vue.js (or other frontend frameworks) or object-oriented programming or the cunning to know them
  • Solution-oriented thinking

Kontakt

If you are interested in this topic, please send your current transcript along with your CV and a short motivation to one of the supervisors' email:

Yushen.Zhang+Apply@cit.TUM.de

Betreuer:

Yushen Zhang

GAN-Based Panoptic-Aware Image Synthesis

Stichworte:
Deep Learning, Semantic Image Synthesis, GANs

Beschreibung

Semantic image synthesis based only on adversarial supervision has recently made remarkable progress. Different to traditional GAN-based approaches, "OASIS" has redesigned the purpose of the discriminator as a N+1 semantic segmentation network, directly using the given semantic label maps as the ground truth for training. By providing stronger supervision to the discriminator as well as to the generator through spatially- and semantically-aware discriminator feedback, OASIS has achieved SOA performance and remains a strong baseline even for powerful diffusion-based models, such as https://arxiv.org/pdf/2207.00050.pdf. 

Despite its great success, it is well known that semantic image synthesis based only on semantic maps often fails in complex environments where multiple instances occlude each other.

The goal of this work is to investigate whether OASIS can be extended to the panoptic case, both from the perspective of the learning objective and the network architecture.

Your work:

  • Literature review of state-of-the-art semantic/ panoptic-aware image synthesis methods, e.g., https://arxiv.org/abs/2012.04781, https://arxiv.org/pdf/2004.10289.pdf.
  • Analysis and identification of suitable panoptic segmentation backbones/ learning objectives. Possible starting point: https://arxiv.org/pdf/2207.04044.pdf.
  • Development of a prototype based on https://github.com/boschresearch/OASIS + evaluation thereof and comparison to the current state-of-the-art.
  • Optional: opportunity to contribute to publications.

 

Voraussetzungen

Requirements:

  • Solid background in machine learning, as well as Python and common deep learning libraries such as TensorFlow or PyTorch.
  • Self-motivation.

 

Kontakt

If you are interested, please contact:

Körber, Nikolai (nikolai.koerber@tum.de) with your CV and transcripts.

Betreuer:

Nikolai Körber

Transformer-Based Transform Coding

Stichworte:
Deep Learning, Transform Coding, Transformer

Beschreibung

Transformer-based transform coding has shown to attain a better rate-distortion-computation trade-off compared to existing solutions. Unlike CNNs, the self-attention mechanism within transformer blocks provides a more general compute paradigm that greatly helps to capture long-range dependencies. However, its great potential is accompanied by a quadratic complexity, which is why a variety of efficient alternatives have been proposed, all with their respective advantages and disadvantages.

Recent work has primarily focused on windowed attention, e.g., “Swin Transformer”, thanks to its hierarchical design and excellent scaling properties. It remains however unclear how much the attention window pattern affects the overall compression performance.

The goal of this work is to analyze and compare current transformer-based solutions specifically suited for dense prediction tasks/ image/ video compression.

Your work:

  • Literature review of state-of-the-art transformer-based coding methods, e.g., https://openreview.net/pdf?id=IDwN6xjHnK8.
  • Analysis and identification of efficient attention mechanisms suitable for dense prediction tasks/ image/video compression. Possible starting point: https://github.com/tensorflow/compression/discussions/151
  • Development of several prototypes based on https://github.com/Nikolai10/SwinT-ChARM + evaluation thereof and comparison to the current state-of-the-art.
  • Optional: opportunity to contribute to publications.

Voraussetzungen

Requirements:

  • Solid background in machine learning, as well as Python and common deep learning libraries such as TensorFlow or PyTorch.
  • Self-motivation.

Kontakt

If you are interested, please contact:

Körber, Nikolai (nikolai.koerber@tum.de) with your CV and transcripts.

Betreuer:

Nikolai Körber

Implementation of an STL library for online web platform

Stichworte:
Microfluidics, Lab-On-Chip, Programming
Kurzbeschreibung:
Analysis and implementation of Stereolithography Language (STL) for 3D-printed microfluidics

Beschreibung

Microfluidic automation – the automated routing, dispensing, mixing, and/or separation of fluids through microchannels – generally remains a slowly-spreading technology because device fabrication requires sophisticated facilities, and the technology’s use demands expert operators. Integrating microfluidic automation in devices has involved specialized multi-layering and bonding approaches. Stereolithography is an assembly-free, 3D-printing technique that is emerging as an efficient alternative for rapidly prototyping biomedical devices. 

The objective of this project is to provide scientists with an easy-to-use microfluidic chip modelling and generation backend tool, the output of which can be directly printed by a high-precision 3D-Printer, and spare scientists of different disciplines from spending excessive time learning complex 3D-Modeling software but also enable them to produce self-designed microfluidic chips in a cost- and time-efficient manner.

Voraussetzungen

  • Knowledge and experience in web design and web development
  • Good knowledge of HTML5, CSS, JavaScript or the wiliness to learn them
  • Basic knowledge of jQuery and Vue.js (or other frontend frameworks) or the wiliness to learn them
  • Solution-oriented thinking

 

Kontakt

If you are interested in this topic, please send your current transcript along with your CV and a short motivation to one of the supervisors' email:

Yushen.Zhang+Apply@cit.TUM.de

Betreuer:

Yushen Zhang

Exploring the relationship between weights and accuracy of neural networks

Stichworte:
Neural network

Beschreibung

In neural networks, some weights are not important to the accuracy of neural networks, indicating that there exists redundancy in neural networks. This redundancy can be used to adjust the shape of weight distributions of neural networks. This adjustment of weight distributions can be achieved by adding penalties in the cost function of neural networks during software training. For example, Figure 1 shows an adjustment of weight distribution by adding penalties during software training.

 

In this bachelor thesis, the tradeoff between the accuracy of neural networks and the shape of weight distributions will be explored. In addition, how the pruning affects this tradeoff will also be explored.

Kontakt

If you are interested in this topic for bachelor thesis, please contact: 

Dr.-Ing. Li Zhang (grace-li.zhang@tum.de) with your CV and transcripts.

Betreuer:

Li Zhang

Masterarbeiten

Reservoir Computing for Power Modeling of Black-Box Sequential Circuits

Beschreibung

Machine learning is getting strong attention in circuit design and electronic design automation. One use case for it would be the generation of accurate power models for intellectual property (IP) blocks [1]. The providers of these blocks are interested in keeping their knowledge about optimized designs secret(black-box IP blocks). This limits the possibility for power modeling, as classical methods would require and reveal information about the structure of the implementation. Here, machine learning can support in generating opaque power models. Models using graph attention networks [2], feed-forward neural networks, reservoir computing or deep spline networks [3] could be used.

 

One specific topic here would be a suitable power modelling technique for sequential circuits. In the black-box regime, only primary inputs and outputs are observable and therefore, the internal state of the system is hidden. This limited information has to be sufficient to perform accurate power dissipation estimation under various workloads. Reservoir computing may be here a suitable method. In contrast to classical reservoir computing, the knowledge about the structure of the circuit could be used to have an engineered reservoir.

 

The goal of this project would be to generate a power estimation framework for sequential circuits.  Therefore, in a literature research the opportunities of reservoir computing for this application should be investigated. Based on the findings, a power model should be generated for a reference sequential circuit (e.g. an open source RISC-V core). Furthermore, the resulting model could be generalized in a framework for estimation model generation.

 

[1] ZHANG, Yanqing; REN, Haoxing; KHAILANY, Brucek. GRANNITE: Graph neural network inference for transferable power estimation. In: 2020 57th ACM/IEEE Design Automation Conference (DAC). IEEE, 2020. S. 1-6.

[2] XIE, Zhiyao, et al. Pre-Placement Net Length and Timing Estimation by Customized Graph Neural Network. IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems, 2022.

[3] BOHRA, Pakshal, et al. Learning activation functions in deep (spline) neural networks. IEEE Open Journal of Signal Processing, 2020, 1. Jg., S. 295-309.

 

 

 

Voraussetzungen

  • Interest in power modeling for ASIC circuits
  • Knowledge in machine learning (preferably in reservoir computing)
  • Basic knowledge in the circuit design flow
  • Good knowledge in python or C++
  • Ability to work independently

Kontakt

If you are interested in this topic, contact me at: philipp.fengler@tum.de

Betreuer:

Philipp Fengler

Comparison of Machine Learning Methods for Opaque Black-Box Power Modeling

Beschreibung

 

Machine learning is getting strong attention in circuit design and electronic design automation. One use case for it would be the generation of accurate power models for intellectual property (IP) blocks [1]. The providers of these blocks are interested in keeping their knowledge about optimized designs secret(black-box IP blocks). This limits the possibility for power modeling, as classical methods would require and reveal information about the structure of the implementation. Here, machine learning can support in generating opaque power models. Models using graph attention networks [2], feed-forward neural networks, reservoir computing or deep spline networks [3] could be used.

 

But, it is questionable, how opaque are the resulting models? If one would consider single modifications on a circuit netlist (e.g. optimizing only a single connection). Would this change also be observable in the differences between the resulting power models (e.g. as only very small regions of the model would change)? If this is the case, one could maybe infer from a set of simple modifications a significant amount of information about the original circuit design.

 

The goal of this project would be to investigate these questions. Therefore, in an existing framework for power model generation, different ML method need to be implemented. Then, for suitable benchmark designs, such single optimizations steps should be generated and the resulting power models investigated.

 

 

[1] ZHANG, Yanqing; REN, Haoxing; KHAILANY, Brucek. GRANNITE: Graph neural network inference for transferable power estimation. In: 2020 57th ACM/IEEE Design Automation Conference (DAC). IEEE, 2020. S. 1-6.

[2] XIE, Zhiyao, et al. Pre-Placement Net Length and Timing Estimation by Customized Graph Neural Network. IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems, 2022.

[3] BOHRA, Pakshal, et al. Learning activation functions in deep (spline) neural networks. IEEE Open Journal of Signal Processing, 2020, 1. Jg., S. 295-309.

 

 

Voraussetzungen

  • Profound knowledge in machine learning (preferably in reservoir computing and deep neural networks)
  • Knowledge of digital circuit design (preferably also in the ASIC design flow)
  • Good knowledge in python
  • Ability to work independently

Kontakt

If you are interested in this topic, please contact me at: philipp.fengler@tum.de

Betreuer:

Philipp Fengler

Implementation of a DXF library for microfluidics design software

Beschreibung

DXF is short for Drawing Exchange Format or Drawing Interchange Format and is a vector file type. Engineers, designers, and architects often use the DXF format for drawings during product design. DXF is widely used in industrial production. Many devices such as printers, laser cutters, CNC machining, etc. accept DXF format as input. In this project, we would like you to implement a generic DXF library that can be used by different software to produce designs in DXF format. 

Voraussetzungen

  • Knowledge and experience in web design and web development or desktop application development
  • Good understanding of JavaScript and PHP or Java Spring Boot or the wiliness to learn them
  • Basic knowledge of Vue.js (or other frontend frameworks) or object-oriented programming or the cunning to know them
  • Solution-oriented thinking

Kontakt

If you are interested in this topic, please send your current transcript along with your CV and a short motivation to one of the supervisors' email:

Yushen.Zhang+Apply@cit.TUM.de

Betreuer:

Yushen Zhang

GAN-Based Panoptic-Aware Image Synthesis

Stichworte:
Deep Learning, Semantic Image Synthesis, GANs

Beschreibung

Semantic image synthesis based only on adversarial supervision has recently made remarkable progress. Different to traditional GAN-based approaches, "OASIS" has redesigned the purpose of the discriminator as a N+1 semantic segmentation network, directly using the given semantic label maps as the ground truth for training. By providing stronger supervision to the discriminator as well as to the generator through spatially- and semantically-aware discriminator feedback, OASIS has achieved SOA performance and remains a strong baseline even for powerful diffusion-based models, such as https://arxiv.org/pdf/2207.00050.pdf. 

Despite its great success, it is well known that semantic image synthesis based only on semantic maps often fails in complex environments where multiple instances occlude each other.

The goal of this work is to investigate whether OASIS can be extended to the panoptic case, both from the perspective of the learning objective and the network architecture.

Your work:

  • Literature review of state-of-the-art semantic/ panoptic-aware image synthesis methods, e.g., https://arxiv.org/abs/2012.04781, https://arxiv.org/pdf/2004.10289.pdf.
  • Analysis and identification of suitable panoptic segmentation backbones/ learning objectives. Possible starting point: https://arxiv.org/pdf/2207.04044.pdf.
  • Development of a prototype based on https://github.com/boschresearch/OASIS + evaluation thereof and comparison to the current state-of-the-art.
  • Optional: opportunity to contribute to publications.

 

Voraussetzungen

Requirements:

  • Solid background in machine learning, as well as Python and common deep learning libraries such as TensorFlow or PyTorch.
  • Self-motivation.

 

Kontakt

If you are interested, please contact:

Körber, Nikolai (nikolai.koerber@tum.de) with your CV and transcripts.

Betreuer:

Nikolai Körber

Transformer-Based Transform Coding

Stichworte:
Deep Learning, Transform Coding, Transformer

Beschreibung

Transformer-based transform coding has shown to attain a better rate-distortion-computation trade-off compared to existing solutions. Unlike CNNs, the self-attention mechanism within transformer blocks provides a more general compute paradigm that greatly helps to capture long-range dependencies. However, its great potential is accompanied by a quadratic complexity, which is why a variety of efficient alternatives have been proposed, all with their respective advantages and disadvantages.

Recent work has primarily focused on windowed attention, e.g., “Swin Transformer”, thanks to its hierarchical design and excellent scaling properties. It remains however unclear how much the attention window pattern affects the overall compression performance.

The goal of this work is to analyze and compare current transformer-based solutions specifically suited for dense prediction tasks/ image/ video compression.

Your work:

  • Literature review of state-of-the-art transformer-based coding methods, e.g., https://openreview.net/pdf?id=IDwN6xjHnK8.
  • Analysis and identification of efficient attention mechanisms suitable for dense prediction tasks/ image/video compression. Possible starting point: https://github.com/tensorflow/compression/discussions/151
  • Development of several prototypes based on https://github.com/Nikolai10/SwinT-ChARM + evaluation thereof and comparison to the current state-of-the-art.
  • Optional: opportunity to contribute to publications.

Voraussetzungen

Requirements:

  • Solid background in machine learning, as well as Python and common deep learning libraries such as TensorFlow or PyTorch.
  • Self-motivation.

Kontakt

If you are interested, please contact:

Körber, Nikolai (nikolai.koerber@tum.de) with your CV and transcripts.

Betreuer:

Nikolai Körber

Design of a Hardware Multi-input FIFO

Stichworte:
Digital Design, FIFO

Beschreibung

Do you want to learn more about Weight Compression and Hardware Acceleration of Neural Networks? Then this Master thesis position is your opportunity to become a part of this exciting journey. You will be developing digital designs for a multi-input FIFO which plays a crucial role in the Hardware Golomb-Rice decoder. We offer you an international working environment and freedom to apply your own ideas and learnings to create amazing new designs. We will be happy to receive your application!

In your new role you will:
• Make yourself familiar with the current design of the decoder.
• Get to know the Infineon hardware generation framework.
• Implement a multi-input FIFO.
• Simulate and Synthesize the RTL designs

 

Voraussetzungen

Profile

You are best equipped for this task if you:


• Are currently studying Electrical Engineering, Informatics or something similar
• Bring knowledge about Electronic Design Automation/Digital Design
• Are familiar with programming in Verilog/VHDL and Python
• Are familiar with Vivado. Familiarity with Design Compiler is a plus
• Are experienced with Git and Linux CLI
• Good command in English


Please attach the following documents to your application:
• CV in English
• Certificate of enrollment at university
• Latest grades transcript

Kontakt

Contact:

Wolfgang.ecker@infineon.com

Mounika.vaddeboina@infineon.com

Betreuer:

Wolfgang Ecker - Mounika Vaddeboina (Infineon Technologies AG)

Implementation of an STL library for online web platform

Stichworte:
Microfluidics, Lab-On-Chip, Programming
Kurzbeschreibung:
Analysis and implementation of Stereolithography Language (STL) for 3D-printed microfluidics

Beschreibung

Microfluidic automation – the automated routing, dispensing, mixing, and/or separation of fluids through microchannels – generally remains a slowly-spreading technology because device fabrication requires sophisticated facilities, and the technology’s use demands expert operators. Integrating microfluidic automation in devices has involved specialized multi-layering and bonding approaches. Stereolithography is an assembly-free, 3D-printing technique that is emerging as an efficient alternative for rapidly prototyping biomedical devices. 

The objective of this project is to provide scientists with an easy-to-use microfluidic chip modelling and generation backend tool, the output of which can be directly printed by a high-precision 3D-Printer, and spare scientists of different disciplines from spending excessive time learning complex 3D-Modeling software but also enable them to produce self-designed microfluidic chips in a cost- and time-efficient manner.

Voraussetzungen

  • Knowledge and experience in web design and web development
  • Good knowledge of HTML5, CSS, JavaScript or the wiliness to learn them
  • Basic knowledge of jQuery and Vue.js (or other frontend frameworks) or the wiliness to learn them
  • Solution-oriented thinking

 

Kontakt

If you are interested in this topic, please send your current transcript along with your CV and a short motivation to one of the supervisors' email:

Yushen.Zhang+Apply@cit.TUM.de

Betreuer:

Yushen Zhang

Automatic Generation of RISC-V Special Instructions in SW Toolchains

Kurzbeschreibung:
In this thesis, a method and implementation should be developed in order to automatically generate patches for the LLVM and GCC toochain from a formal definition of a special instruction.

Beschreibung

RISC-V is a new, open instruction set architecture (ISA) that, as a core feature, can be extended with special instructions to customize embedded processors to special applications such as frm the control and machine learning domain.

We already developed a customizable simulator named ETISS, that can quickly evaluate the benefit of special instructions for a given application. Next to the core, also the compiler and assembler support for creating a binary from embedded C code is required by designers to exploit performance benefits of special instructions.

In this thesis, a method and implementation should be developed in order to automatically generate patches for the LLVM and GCC toochain from a formal definition of a special instruction. There are various levels of special instruction support possible in the toolchain, that should be explored within this thesis.

Betreuer:

Block-wise Training for Systolic Arrays of Digital Neural Network Accelerators

Stichworte:
Neural Network; Systolic Arrays; Block-wise Training

Beschreibung

In recent years, deep neural networks (DNNs) have been widely applied in various fields, e.g., image/speech recognition. In DNNs, there are a large number of multiply-accumulate (MAC) operations. To accelerate MAC operations in DNNs, systolic arrays are introduced as an attractive platform due to their high degree of concurrent computation and high data reuse rate. Recently, various state of the art hardware accelerators using systolic arrays or properties of systolic arrays have been proposed. TPU is the most well-known accelerator based on systolic arrays. Systolic arrays have a regular structure where Processing Elements (PEs) are replicated and connected together to process data in a pipelined fashion. Figure 1 shows the structure of the systolic array. However, weights of neural networks after unstructured pruning usually exhibit irregular patterns, as shown in Figure 2. Implementing MAC operations with such irregular weight patterns on systolic arrays with regular designs, might result in an underutilization of hardware resources.

In this master thesis, a block-wise neural network training method will be explored to fully exploit the benefits of systolic arrays. 

 

Kontakt

If you are interested in this topic for master thesis, please contact: 

Dr.-Ing. Li Zhang (grace-li.zhang@tum.de) with your CV and bachelor and master transcripts.

Betreuer:

Li Zhang

Neural Network Evaluation and Enhancement Considering Quantization

Stichworte:
Neural Network, Quantization

Beschreibung

Neural networks as shown in Figure 1 (see the attached pdf) have successfully been applied to solve complex problems such as speech/image processing. To improve computing accuracy, the depth of neural networks has steadily increased significantly, leading to deep neural networks (DNNs). The increasing complexity has put massive demands on computing power and triggered intensive research on hardware acceleration for neuromorphic computing in recent years. 

The computation function at a neuron in a neural network can be considered as an incompletely specified truth table. The known entries in such a table are determined by the training data. Since training data are usually a small subset of all entries in the truth table, we need to estimate the other entries to realize the logic design with the truth table. The concept of this technique is illustrated in Figure 2 (see the attached pdf), where the neural network is quantized so that the inputs and the outputs of neurons are represented by binary values.

In the quantization, fewer bits reduce resource usage, but the accuracy of the computation may also degrades. In this thesis, a balance between hardware resource and computation accuracy of neural networks will be explored. To compensate the accuracy degradation caused by quantization, the structures of neural networks may also be modified together with quantization to achieve an overall good area efficiency and computation accuracy. The major tasks of this thesis may include:

1. Quantize inputs and outputs of neurons into different number of bits to evaluate the relation between the number of bits and the accuracy of the neural networks.

2. Modification of neural network structures for a tradeoff between accuracy, number of quantization bits and required number of computation operations.

Kontakt

If you are interested in this topic for master thesis, please contact: 

 Amro Eldebiky (amro.eldebiky@tum.de)  with your CV and transcripts.

 

Betreuer:

Li Zhang

Neural Network Enhancement for Robustness of RRAM-based Design

Stichworte:
Neural Network, RRAM, Robustness

Beschreibung

RRAM-based crossbars shown in Figure 1 are a promising hardware platform to accelerate computations in neural networks. Before such a crossbar can be used as an accelerator for neural networks, RRAM cells should be programmed to target resistances to represent weights in neural networks. However, this process degrades the valid range of the resistances of RRAM cells from the fresh state, called aging effect. Therefore, after a certain number of programming iterations, the RRAM cells cannot be programmed reliably anymore, affecting the classification accuracy of neural networks negatively. 

 

In neural networks, the weights may have different distributions to achieve the same accuracy. This inherent computation redundancy can be used to reduce the stress on specific and/or overall devices.  Figure 2(a) shows the weight distribution after traditional software training. However, weights in the training can actually be adjusted to avoid those values that cause large currents and thus aging effects. Consequently, the weight distribution after modified training can have a different shape as shown in Figure 2(b). 

 

In this master thesis, an algorithm will be developed to examine the shapes of weight distribution in neural networks and the mapping of weights with respect to aging models. Defects of devices after manufacturing will also be investigated and countered by training and weight mapping. 

Kontakt

If you are interested in this topic for master thesis, please contact: 

 Amro Eldebiky (amro.eldebiky@tum.de) with your CV and transcripts.

Betreuer:

Li Zhang

Interdisziplinäre Projekte

Implementation of a DXF library for microfluidics design software

Beschreibung

DXF is short for Drawing Exchange Format or Drawing Interchange Format and is a vector file type. Engineers, designers, and architects often use the DXF format for drawings during product design. DXF is widely used in industrial production. Many devices such as printers, laser cutters, CNC machining, etc. accept DXF format as input. In this project, we would like you to implement a generic DXF library that can be used by different software to produce designs in DXF format. 

Voraussetzungen

  • Knowledge and experience in web design and web development or desktop application development
  • Good understanding of JavaScript and PHP or Java Spring Boot or the wiliness to learn them
  • Basic knowledge of Vue.js (or other frontend frameworks) or object-oriented programming or the cunning to know them
  • Solution-oriented thinking

Kontakt

If you are interested in this topic, please send your current transcript along with your CV and a short motivation to one of the supervisors' email:

Yushen.Zhang+Apply@cit.TUM.de

Betreuer:

Yushen Zhang

Implementation of an STL library for online web platform

Stichworte:
Microfluidics, Lab-On-Chip, Programming
Kurzbeschreibung:
Analysis and implementation of Stereolithography Language (STL) for 3D-printed microfluidics

Beschreibung

Microfluidic automation – the automated routing, dispensing, mixing, and/or separation of fluids through microchannels – generally remains a slowly-spreading technology because device fabrication requires sophisticated facilities, and the technology’s use demands expert operators. Integrating microfluidic automation in devices has involved specialized multi-layering and bonding approaches. Stereolithography is an assembly-free, 3D-printing technique that is emerging as an efficient alternative for rapidly prototyping biomedical devices. 

The objective of this project is to provide scientists with an easy-to-use microfluidic chip modelling and generation backend tool, the output of which can be directly printed by a high-precision 3D-Printer, and spare scientists of different disciplines from spending excessive time learning complex 3D-Modeling software but also enable them to produce self-designed microfluidic chips in a cost- and time-efficient manner.

Voraussetzungen

  • Knowledge and experience in web design and web development
  • Good knowledge of HTML5, CSS, JavaScript or the wiliness to learn them
  • Basic knowledge of jQuery and Vue.js (or other frontend frameworks) or the wiliness to learn them
  • Solution-oriented thinking

 

Kontakt

If you are interested in this topic, please send your current transcript along with your CV and a short motivation to one of the supervisors' email:

Yushen.Zhang+Apply@cit.TUM.de

Betreuer:

Yushen Zhang

Enable Remote Execution of Benchmarks using the MLonMCU TinyML Deployment Tool

Stichworte:
MLonMCU, TinyML, Embedded Machine Learning, Benchmark, Python, Remote, Server
Kurzbeschreibung:
MLonMCU is an open source TinyML Benchmarking Flow maintained by our chair. While it was designed for batch processing to exploit parallelism during complex benchmarking sessions, the total execution time of a benchmark is limited by the amount out computational resources available on the local device. In this project you will design and implement a remote execution feature for MLonMCU which allows offloading individual benchmarking runs to a number of remote devices.

Beschreibung

The required steps can be described as follows:

  • Get used to the MLonMCU Benchmarking flow
  • Propose a concept for a remote execution of benchmarks
  • Implement remote execution protocol
  • Add more features to improve benchmarking throughput
  • Add detailed documentation

Voraussetzungen

  • Experience with networking protocols
  • Good Python programming
  • Ideally experience working with UNIX-like operating systems

Betreuer:

Philipp van Kempen

Forschungspraxis (Research Internships)

Reservoir Computing for Power Modeling of Black-Box Sequential Circuits

Beschreibung

Machine learning is getting strong attention in circuit design and electronic design automation. One use case for it would be the generation of accurate power models for intellectual property (IP) blocks [1]. The providers of these blocks are interested in keeping their knowledge about optimized designs secret(black-box IP blocks). This limits the possibility for power modeling, as classical methods would require and reveal information about the structure of the implementation. Here, machine learning can support in generating opaque power models. Models using graph attention networks [2], feed-forward neural networks, reservoir computing or deep spline networks [3] could be used.

 

One specific topic here would be a suitable power modelling technique for sequential circuits. In the black-box regime, only primary inputs and outputs are observable and therefore, the internal state of the system is hidden. This limited information has to be sufficient to perform accurate power dissipation estimation under various workloads. Reservoir computing may be here a suitable method. In contrast to classical reservoir computing, the knowledge about the structure of the circuit could be used to have an engineered reservoir.

 

The goal of this project would be to generate a power estimation framework for sequential circuits.  Therefore, in a literature research the opportunities of reservoir computing for this application should be investigated. Based on the findings, a power model should be generated for a reference sequential circuit (e.g. an open source RISC-V core). Furthermore, the resulting model could be generalized in a framework for estimation model generation.

 

[1] ZHANG, Yanqing; REN, Haoxing; KHAILANY, Brucek. GRANNITE: Graph neural network inference for transferable power estimation. In: 2020 57th ACM/IEEE Design Automation Conference (DAC). IEEE, 2020. S. 1-6.

[2] XIE, Zhiyao, et al. Pre-Placement Net Length and Timing Estimation by Customized Graph Neural Network. IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems, 2022.

[3] BOHRA, Pakshal, et al. Learning activation functions in deep (spline) neural networks. IEEE Open Journal of Signal Processing, 2020, 1. Jg., S. 295-309.

 

 

 

Voraussetzungen

  • Interest in power modeling for ASIC circuits
  • Knowledge in machine learning (preferably in reservoir computing)
  • Basic knowledge in the circuit design flow
  • Good knowledge in python or C++
  • Ability to work independently

Kontakt

If you are interested in this topic, contact me at: philipp.fengler@tum.de

Betreuer:

Philipp Fengler

Enable Remote Execution of Benchmarks using the MLonMCU TinyML Deployment Tool

Stichworte:
MLonMCU, TinyML, Embedded Machine Learning, Benchmark, Python, Remote, Server
Kurzbeschreibung:
MLonMCU is an open source TinyML Benchmarking Flow maintained by our chair. While it was designed for batch processing to exploit parallelism during complex benchmarking sessions, the total execution time of a benchmark is limited by the amount out computational resources available on the local device. In this project you will design and implement a remote execution feature for MLonMCU which allows offloading individual benchmarking runs to a number of remote devices.

Beschreibung

The required steps can be described as follows:

  • Get used to the MLonMCU Benchmarking flow
  • Propose a concept for a remote execution of benchmarks
  • Implement remote execution protocol
  • Add more features to improve benchmarking throughput
  • Add detailed documentation

Voraussetzungen

  • Experience with networking protocols
  • Good Python programming
  • Ideally experience working with UNIX-like operating systems

Betreuer:

Philipp van Kempen

Automatic Generation of RISC-V Special Instructions in SW Toolchains

Kurzbeschreibung:
In this thesis, a method and implementation should be developed in order to automatically generate patches for the LLVM and GCC toochain from a formal definition of a special instruction.

Beschreibung

RISC-V is a new, open instruction set architecture (ISA) that, as a core feature, can be extended with special instructions to customize embedded processors to special applications such as frm the control and machine learning domain.

We already developed a customizable simulator named ETISS, that can quickly evaluate the benefit of special instructions for a given application. Next to the core, also the compiler and assembler support for creating a binary from embedded C code is required by designers to exploit performance benefits of special instructions.

In this thesis, a method and implementation should be developed in order to automatically generate patches for the LLVM and GCC toochain from a formal definition of a special instruction. There are various levels of special instruction support possible in the toolchain, that should be explored within this thesis.

Betreuer:

Ingenieurpraxis

Implementation of a DXF library for microfluidics design software

Beschreibung

DXF is short for Drawing Exchange Format or Drawing Interchange Format and is a vector file type. Engineers, designers, and architects often use the DXF format for drawings during product design. DXF is widely used in industrial production. Many devices such as printers, laser cutters, CNC machining, etc. accept DXF format as input. In this project, we would like you to implement a generic DXF library that can be used by different software to produce designs in DXF format. 

Voraussetzungen

  • Knowledge and experience in web design and web development or desktop application development
  • Good understanding of JavaScript and PHP or Java Spring Boot or the wiliness to learn them
  • Basic knowledge of Vue.js (or other frontend frameworks) or object-oriented programming or the cunning to know them
  • Solution-oriented thinking

Kontakt

If you are interested in this topic, please send your current transcript along with your CV and a short motivation to one of the supervisors' email:

Yushen.Zhang+Apply@cit.TUM.de

Betreuer:

Yushen Zhang

Implementation of an STL library for online web platform

Stichworte:
Microfluidics, Lab-On-Chip, Programming
Kurzbeschreibung:
Analysis and implementation of Stereolithography Language (STL) for 3D-printed microfluidics

Beschreibung

Microfluidic automation – the automated routing, dispensing, mixing, and/or separation of fluids through microchannels – generally remains a slowly-spreading technology because device fabrication requires sophisticated facilities, and the technology’s use demands expert operators. Integrating microfluidic automation in devices has involved specialized multi-layering and bonding approaches. Stereolithography is an assembly-free, 3D-printing technique that is emerging as an efficient alternative for rapidly prototyping biomedical devices. 

The objective of this project is to provide scientists with an easy-to-use microfluidic chip modelling and generation backend tool, the output of which can be directly printed by a high-precision 3D-Printer, and spare scientists of different disciplines from spending excessive time learning complex 3D-Modeling software but also enable them to produce self-designed microfluidic chips in a cost- and time-efficient manner.

Voraussetzungen

  • Knowledge and experience in web design and web development
  • Good knowledge of HTML5, CSS, JavaScript or the wiliness to learn them
  • Basic knowledge of jQuery and Vue.js (or other frontend frameworks) or the wiliness to learn them
  • Solution-oriented thinking

 

Kontakt

If you are interested in this topic, please send your current transcript along with your CV and a short motivation to one of the supervisors' email:

Yushen.Zhang+Apply@cit.TUM.de

Betreuer:

Yushen Zhang