Date: June 3rd, 17:30Location: Building 80 Room 00-021 The unit invites everyone interested to the next social event on June 3rd! Get ready for an engaging gathering filled with insightful discussions. A great event to connect with the AI community in Freiburg! This time, there are two ten-minute presentations. The talks are followed by a Read more
Speaker: Arber ZelaDate: 29th April 2024 Pareto front profiling in multi-objective optimization (MOO), i.e. finding a diverse set of Pareto optimal solutions, is challenging, especially with expensive objectives like neural network training. Typically, in MOO neural architecture search (NAS), we aim to balance performance and hardware metrics across devices. Prior Read more
Speaker: Josif GrabockaDate: 2022-09-23 Josif Grabocka from the Representation Learning Research Group at Uni Freiburg will give a talk titled “Efficient Hyperparameter Optimization in the Age of Deep Learning“. Abstract Hyperparameter Optimization (HPO) is essential in designing state-of-the-art Machine Learning systems. Unfortunately, existing HPO techniques are not efficient enough for Read more
Samuel Müller from the Machine Learning Lab will give a talk titled “Prior-data Fitted Networks (PFNs): Use neural networks for 100x faster Bayesian predictions“. Abstract Bayesian methods can be expensive and complicated to approximate with e.g. Markov Chain Monte Carlo (MCMC) or Variational Inference (VI) approaches. Prior-data Fitted Networks (PFNs) Read more
Speaker: Daniel HonerkampDate: 2022-08-26 Abstract Mobile manipulation remains a critical challenge across both service and industrial settings and is a key component to visions such as household assistants. But for this it requires the combination of a wide range of capabilities, such as perception and exploration in unknown environments while Read more
Speaker: Chenguang HuangDate: 2022-08-12 Abstract Robot navigation has been an actively researched challenge for decades. With different focuses, navigation goals can be defined in many different ways such as goal images, relative positions, semantic objects, and sound sources. Recently, with the advances in both computer vision and natural language processing Read more
Speaker: Adam KortylewskiDate: 2022-07-29 Abstract Deep learning sparked a tremendous increase in the performance of computer vision systems over the past decade. However, Deep Neural Networks (DNNs) are still far from reaching human-level performance at visual recognition tasks. The most important limitation of DNNs is that they fail to give Read more
Speaker: Jens KoberDate: 2022-06-24 Abstract The acquisition and self-improvement of novel motor skills is among the most important problems in robotics. I will discuss various learning techniques we developed that enable robots to have complex interactions with their environment and humans. Complexity arises from dealing with high-dimensional input data, non-linear Read more
Speaker: Frank HutterDate: 2022-05-05 Abstract Deep Learning (DL) has been able to revolutionize learning from raw data (images, text, speech, etc) by replacing domain-specific hand-crafted features with features that are jointly learned for the particular task at hand. I propose to take deep learning to the next level, by also Read more
Speaker: Arbër ZelaDate: 2022-04-15 Abstract Ensembles of neural networks achieve superior performance compared to standalone networks not only in terms of accuracy on in-distribution data but also on data with distributional shift alongside improved uncertainty calibration. Diversity among networks in an ensemble is believed to be key for building strong Read more