PhD - Robust Ensembles of Deep Probabilistic Models
- Robert-Bosch-Campus 1, 71272 Renningen, Germany
- Legal Entity: Robert Bosch GmbH
Do you want beneficial technologies being shaped by your ideas? Whether in the areas of mobility solutions, consumer goods, industrial technology or energy and building technology – with us, you will have the chance to improve quality of life all across the globe. Welcome to Bosch.
The Robert Bosch GmbH is looking forward to your application!
Probabilistic modeling provides a framework to extract useful patterns from data. Specifically, deep latent variable models combine the flexibility of neural networks with the expressiveness of latent variable models. The key to the success of such methods is the match between the model complexity and the difficulty of the problem. In addition, the data-efficiency of the method has to match the amount of available data. A general rule of thumb is that more complex models will require more data to accurately capture the underlying distribution. The goal of this PhD project is to explore the controlled trade-off between model interpretability, model complexity, and sensitivity to the quality and amount of available data and to exploit these insights to develop new custom deep latent variable models for real-world applications. To make the deep latent variable models more data-efficient and more robust, a special focus of the project will be on the development of ensemble methods. Ensemble methods are popular in predictive machine learning, where they are used to combine the predictions of multiple models into a single, provably more reliable prediction. How to best combine the patterns extracted by a number of deep latent variable models remains an unsolved challenge. Tackling it, promises more robust unsupervised machine learning methods.
During your PhD you will be part of the active research team at the Bosch Center for Artificial Intelligence (BCAI, www.bosch-ai.com).
Your tasks will include:
- Invention of novel ways to combine probabilistic models with neural networks.
- Prototype implementations and benchmarking on real-world data sets.
- Literature screening and building close contact with the academic community.
- Active participation in the academic activities of the BCAI research team.
- Publications in top-tier conferences (ICML, NIPS, ICLR, AISTATS, etc.) and journals (JMLR, PAMI, etc.).
- Personality: highly motivated, excellent communications and theoretical skills
- Working Practice: collaborative mindset and independent problem solving
- Experience and Knowledge: programming experience in python, preferably with tensorflow or another machine learning library, prior experience implementing a machine learning algorithm and running it on real data is a plus
- Languages: excellent in English (written and spoken)
- Education: excellent degree (Master) in machine learning, mathematics, computer science, statistics, physics, or a related field
Please submit all relevant documents (incl. curriculum vitae, certificates) and a cover letter emphasizing why you want to do a PhD in machine learning and what you are hoping to learn during your PhD at the Bosch Center for Artificial Intelligence.