Refine
Year of publication
- 2024 (1)
- 2023 (3)
- 2020 (7)
- 2019 (3)
- 2018 (5)
- 2017 (5)
- 2016 (3)
- 2015 (13)
- 2014 (4)
- 2013 (3)
- 2012 (6)
- 2011 (3)
- 2010 (9)
- 2009 (8)
- 2008 (15)
- 2007 (10)
- 2006 (3)
- 2005 (9)
- 2004 (3)
- 2003 (6)
- 2002 (6)
- 2001 (6)
- 2000 (2)
- 1999 (4)
- 1998 (4)
- 1997 (2)
- 1996 (4)
- 1995 (3)
- 1994 (1)
- 1992 (1)
- 1991 (1)
- 1990 (1)
- 1986 (1)
- 1985 (2)
- 1984 (2)
- 1981 (1)
- 1980 (2)
- 1977 (2)
- 1975 (1)
Document Type
- Book chapter (165) (remove)
Has Fulltext
- no (165) (remove)
Institute
- Mathematical Optimization (53)
- Visual and Data-centric Computing (35)
- Numerical Mathematics (34)
- Visual Data Analysis (34)
- Visual Data Analysis in Science and Engineering (20)
- Distributed Algorithms and Supercomputing (13)
- Computational Nano Optics (12)
- Therapy Planning (10)
- Computational Medicine (6)
- Applied Algorithmic Intelligence Methods (5)
Connectomics is a branch of neuroscience that attempts to create a connectome, i.e., a complete map of the neuronal system and all connections between neuronal structures. This representation can be used to understand how functional brain states emerge from their underlying anatomical structures and how dysfunction and neuronal diseases arise. We review the current state-of-the-art of visualization and image processing techniques in the field of connectomics and describe a number of challenges. After a brief summary of the biological background and an overview of relevant imaging modalities, we review current techniques to extract connectivity information from image data at macro-, meso- and microscales. We also discuss data integration and neural network modeling, as well as the visualization, analysis and comparison of brain networks.
The recent advances in machine learning in various fields of applications can be largely attributed to the rise of deep learning (DL) methods and architectures. Despite being a key technology behind autonomous cars, image processing, speech recognition, etc., a notorious problem remains the lack of theoretical understanding of DL and related interpretability and (adversarial) robustness issues. Understanding the specifics of DL, as compared to, say, other forms of nonlinear regression methods or statistical learning, is interesting from a mathematical perspective, but at the same time it is of crucial importance in practice: treating neural networks as mere black boxes might be sufficient in certain cases, but many applications require waterproof performance guarantees and a deeper understanding of what could go wrong and why it could go wrong. It is probably fair to say that, despite being mathematically well founded as a method to approximate complicated functions, DL is mostly still more like modern alchemy that is firmly in the hands of engineers and computer scientists. Nevertheless, it is evident that certain specifics of DL that could explain its success in applications demands systematic mathematical approaches. In this work, we review robustness issues of DL and particularly bridge concerns and attempts from approximation theory to statistical learning theory. Further, we review Bayesian Deep Learning as a means for uncertainty quantification and rigorous explainability.