Master Thesis in Efficient Video Representations Using Hierarchical Predictions
Master Thesis in Efficient Video Representations Using Hierarchical Predictions
Employer Active
Job Alert
You will be updated with latest job alerts via email
Share
Job Alert
You will be updated with latest job alerts via email
Job Description
The goal of this master thesis is to explore innovative methodologies for enhancing the efficiency of deep neural networks in artificial intelligence applications particularly in robotics and autonomous driving.
- During your thesis you will work on developing a temporal predictive extension of existing foundation models to identify and eliminate redundancy in temporal high-dimensional data such as video streams. This approach aims to significantly reduce runtime inefficiencies associated with sequential computations thereby streamlining the inference process and improving overall model performance.
- You will conduct a comprehensive literature review to understand current methodologies.
- Furthermore you will design a novel model extension that incorporates temporal predictive capabilities and you will implement training protocols to optimize the models performance on temporal data.
- Finally you will evaluate the models efficiency in terms of computational and energy consumption and analyze the implications of the findings for real-time AI applications.
Qualifications :
- Education: Master studies in the field of Natural Sciences and Engineering (like Computer Science Math Statistics Physics Cybernetics Electrical Engineering) with very good grades
- Experience and Knowledge: strong knowledge and experience in Machine Learning Deep Learning Computer Vision and Python (PyTorch)
- Personality and Working Practice: you excel at working independently and driving your own projects forward with strong intrinsic motivation
- Languages: fluent in English
Additional Information :
Start: according to prior agreement
Duration: 6 months
Requirement for this thesis is the enrollment at university. Please attach your CV transcript of records examination regulations and if indicated a valid work and residence permit.
Diversity and inclusion are not just trends for us but are firmly anchored in our corporate culture. Therefore we welcome all applications regardless of gender age disability religion ethnic origin or sexual identity.
Need further information about the job
Volker Fischer (Functional Department)
#LI-DNI
Remote Work :
No
Employment Type :
Full-time
Employment Type
Full-time
