Lecture

Uncertainty Quantification and Label Error Detection

Related lectures (30)

Covers fundamental principles, opportunities, and challenges in machine learning.

Introduces Convolutional Neural Networks (CNNs) for autonomous vehicles, covering architecture, applications, and regularization techniques.

Active Learning for Molecular Design

Covers machine learning approaches for material design, practical examples, and software tools for research.

Deep Learning: Edge Detection and Neural Networks

Discusses edge detection techniques and the evolution of deep learning in neural networks.

Delineation: Techniques and Applications

Explores techniques for delineation, including Hough transform, gradient orientation, and shape detection, emphasizing the importance of combining graph-based techniques and machine learning.

Machine Learning Fundamentals

Covers the fundamental concepts of machine learning, including classification, algorithms, optimization, supervised learning, reinforcement learning, and various tasks like image recognition and text generation.

Deep Learning: Convolutional Neural Networks

Covers Convolutional Neural Networks, standard architectures, training techniques, and adversarial examples in deep learning.

Landscape and Generalisation in Deep Learning

Explores the challenges and insights of deep learning, focusing on loss landscape, generalization, and feature learning.

Deep Visual Recognition: Interpretability

Explores deep visual recognition, interpretability, CNN architectures, visual dictionaries, and attention mechanisms.

Perception: Data-Driven Approaches

Explores perception in deep learning for autonomous vehicles, covering image classification, optimization methods, and the role of representation in machine learning.

Edge Detection: Deep Learning Insights

Explores the evolution of edge detection techniques, from Canny to deep learning insights.

Texture Analysis: Statistical and Structural Approaches

Discusses texture analysis in images, focusing on statistical and structural properties, segmentation techniques, and machine learning applications for texture classification.

Transformers in Visual Intelligence

Explores transformers in visual intelligence, focusing on object detection, image synthesis, and feature fusion.

Deep Learning: Convolutional Neural Networks and Training Techniques

Discusses convolutional neural networks, their architecture, training techniques, and challenges like adversarial examples in deep learning.

Robotic Generalization: Tactile Perception and Pose Estimation

Explores robotic generalization, tactile perception, pose estimation, and active learning in uncertain environments.

Autonomous Vehicles: Trajectory Prediction and Social Behavior

Explores challenges in deep learning for autonomous vehicles, emphasizing social behavior modeling and feasible trajectory prediction.

Document Segmentation: dhSegment

Explores the development and improvements of dhSegment, an open-source document segmentation package using PyTorch.

Deep Learning for Autonomous Vehicles: Predictive Models

Explores predictive models and trackers for autonomous vehicles, covering object detection, tracking challenges, neural network-based tracking, and 3D pedestrian localization.

Land Use Mapping in the Alps

Explores soil sealing impact, land use statistics, image segmentation, and random forest classification for sustainable land management.

Quasi-Categories: Active Learning Session

Covers fibrant objects, lift of horns, and the adjunction between quasi-categories and Kan complexes, as well as the generalization of categories and Kan complexes.