@article{SteiningerAbelZiegleretal.2023, author = {Steininger, Michael and Abel, Daniel and Ziegler, Katrin and Krause, Anna and Paeth, Heiko and Hotho, Andreas}, title = {ConvMOS: climate model output statistics with deep learning}, series = {Data Mining and Knowledge Discovery}, volume = {37}, journal = {Data Mining and Knowledge Discovery}, number = {1}, issn = {1384-5810}, doi = {10.1007/s10618-022-00877-6}, url = {http://nbn-resolving.de/urn:nbn:de:bvb:20-opus-324213}, pages = {136-166}, year = {2023}, abstract = {Climate models are the tool of choice for scientists researching climate change. Like all models they suffer from errors, particularly systematic and location-specific representation errors. One way to reduce these errors is model output statistics (MOS) where the model output is fitted to observational data with machine learning. In this work, we assess the use of convolutional Deep Learning climate MOS approaches and present the ConvMOS architecture which is specifically designed based on the observation that there are systematic and location-specific errors in the precipitation estimates of climate models. We apply ConvMOS models to the simulated precipitation of the regional climate model REMO, showing that a combination of per-location model parameters for reducing location-specific errors and global model parameters for reducing systematic errors is indeed beneficial for MOS performance. We find that ConvMOS models can reduce errors considerably and perform significantly better than three commonly used MOS approaches and plain ResNet and U-Net models in most cases. Our results show that non-linear MOS models underestimate the number of extreme precipitation events, which we alleviate by training models specialized towards extreme precipitation events with the imbalanced regression method DenseLoss. While we consider climate MOS, we argue that aspects of ConvMOS may also be beneficial in other domains with geospatial data, such as air pollution modeling or weather forecasts.}, subject = {Klima}, language = {en} } @phdthesis{Selle2007, author = {Selle, Reimer Andreas}, title = {Adaptive Polarization Pulse Shaping and Modeling of Light-Matter Interactions with Neural Networks}, url = {http://nbn-resolving.de/urn:nbn:de:bvb:20-opus-25596}, school = {Universit{\"a}t W{\"u}rzburg}, year = {2007}, abstract = {The technique of ultrafast polarization shaping is applied to a model quantum system, the potassium dimer. The polarization dependence of the multiphoton ionization dynamics in this molecule is first investigated in pump-probe experiments, and it is then more generally addressed and exploited in an adaptive quantum control experiment utilizing near-IR polarization-shaped laser pulses. The extension of these polarization shaping techniques to the UV spectral range is presented, and methods for the generation and characterization of polarization-shaped laser pulses in the UV are introduced. Systematic scans of double-pulse sequences are introduced for the investigation and interpretation of control mechanisms. This concept is first introduced and illustrated for an optical demonstration experiment, and it is then applied for the analysis of the intrapulse dumping mechanism that is observed in the excitation of a large dye molecule in solution with ultrashort laser pulses. Shaped laser pulses are employed as a means for obtaining copious amounts of data on light-matter interactions. Neural networks are introduced as a novel tool for generating computer-based models for these interactions from the accumulated data. The viability of this approach is first tested for second harmonic generation (SHG) and molecular fluorescence processes. Neural networks are then utilized for modeling the far more complex coherent strong-field dynamics of potassium atoms.}, subject = {Lasertechnologie}, language = {en} } @article{SchloerRingHotho2020, author = {Schl{\"o}r, Daniel and Ring, Markus and Hotho, Andreas}, title = {iNALU: Improved Neural Arithmetic Logic Unit}, series = {Frontiers in Artificial Intelligence}, volume = {3}, journal = {Frontiers in Artificial Intelligence}, issn = {2624-8212}, doi = {10.3389/frai.2020.00071}, url = {http://nbn-resolving.de/urn:nbn:de:bvb:20-opus-212301}, year = {2020}, abstract = {Neural networks have to capture mathematical relationships in order to learn various tasks. They approximate these relations implicitly and therefore often do not generalize well. The recently proposed Neural Arithmetic Logic Unit (NALU) is a novel neural architecture which is able to explicitly represent the mathematical relationships by the units of the network to learn operations such as summation, subtraction or multiplication. Although NALUs have been shown to perform well on various downstream tasks, an in-depth analysis reveals practical shortcomings by design, such as the inability to multiply or divide negative input values or training stability issues for deeper networks. We address these issues and propose an improved model architecture. We evaluate our model empirically in various settings from learning basic arithmetic operations to more complex functions. Our experiments indicate that our model solves stability issues and outperforms the original NALU model in means of arithmetic precision and convergence.}, language = {en} } @phdthesis{Ruttor2006, author = {Ruttor, Andreas}, title = {Neural Synchronization and Cryptography}, url = {http://nbn-resolving.de/urn:nbn:de:bvb:20-opus-23618}, school = {Universit{\"a}t W{\"u}rzburg}, year = {2006}, abstract = {Neural networks can synchronize by learning from each other. For that purpose they receive common inputs and exchange their outputs. Adjusting discrete weights according to a suitable learning rule then leads to full synchronization in a finite number of steps. It is also possible to train additional neural networks by using the inputs and outputs generated during this process as examples. Several algorithms for both tasks are presented and analyzed. In the case of Tree Parity Machines the dynamics of both processes is driven by attractive and repulsive stochastic forces. Thus it can be described well by models based on random walks, which represent either the weights themselves or order parameters of their distribution. However, synchronization is much faster than learning. This effect is caused by different frequencies of attractive and repulsive steps, as only neural networks interacting with each other are able to skip unsuitable inputs. Scaling laws for the number of steps needed for full synchronization and successful learning are derived using analytical models. They indicate that the difference between both processes can be controlled by changing the synaptic depth. In the case of bidirectional interaction the synchronization time increases proportional to the square of this parameter, but it grows exponentially, if information is transmitted in one direction only. Because of this effect neural synchronization can be used to construct a cryptographic key-exchange protocol. Here the partners benefit from mutual interaction, so that a passive attacker is usually unable to learn the generated key in time. The success probabilities of different attack methods are determined by numerical simulations and scaling laws are derived from the data. If the synaptic depth is increased, the complexity of a successful attack grows exponentially, but there is only a polynomial increase of the effort needed to generate a key. Therefore the partners can reach any desired level of security by choosing suitable parameters. In addition, the entropy of the weight distribution is used to determine the effective number of keys, which are generated in different runs of the key-exchange protocol using the same sequence of input vectors. If the common random inputs are replaced with queries, synchronization is possible, too. However, the partners have more control over the difficulty of the key exchange and the attacks. Therefore they can improve the security without increasing the average synchronization time.}, language = {en} } @article{PerniaAndradeWengerEspositoetal.2021, author = {Pern{\´i}a-Andrade, Alejandro J. and Wenger, Nikolaus and Esposito, Maria S. and Tovote, Philip}, title = {Circuits for State-Dependent Modulation of Locomotion}, series = {Frontiers in Human Neuroscience}, volume = {15}, journal = {Frontiers in Human Neuroscience}, issn = {1662-5161}, doi = {10.3389/fnhum.2021.745689}, url = {http://nbn-resolving.de/urn:nbn:de:bvb:20-opus-249995}, year = {2021}, abstract = {Brain-wide neural circuits enable bi- and quadrupeds to express adaptive locomotor behaviors in a context- and state-dependent manner, e.g., in response to threats or rewards. These behaviors include dynamic transitions between initiation, maintenance and termination of locomotion. Advances within the last decade have revealed an intricate coordination of these individual locomotion phases by complex interaction of multiple brain circuits. This review provides an overview of the neural basis of state-dependent modulation of locomotion initiation, maintenance and termination, with a focus on insights from circuit-centered studies in rodents. The reviewed evidence indicates that a brain-wide network involving excitatory circuit elements connecting cortex, midbrain and medullary areas appears to be the common substrate for the initiation of locomotion across different higher-order states. Specific network elements within motor cortex and the mesencephalic locomotor region drive the initial postural adjustment and the initiation of locomotion. Microcircuits of the basal ganglia, by implementing action-selection computations, trigger goal-directed locomotion. The initiation of locomotion is regulated by neuromodulatory circuits residing in the basal forebrain, the hypothalamus, and medullary regions such as locus coeruleus. The maintenance of locomotion requires the interaction of an even larger neuronal network involving motor, sensory and associative cortical elements, as well as defined circuits within the superior colliculus, the cerebellum, the periaqueductal gray, the mesencephalic locomotor region and the medullary reticular formation. Finally, locomotor arrest as an important component of defensive emotional states, such as acute anxiety, is mediated via a network of survival circuits involving hypothalamus, amygdala, periaqueductal gray and medullary premotor centers. By moving beyond the organizational principle of functional brain regions, this review promotes a circuit-centered perspective of locomotor regulation by higher-order states, and emphasizes the importance of individual network elements such as cell types and projection pathways. The realization that dysfunction within smaller, identifiable circuit elements can affect the larger network function supports more mechanistic and targeted therapeutic intervention in the treatment of motor network disorders.}, language = {en} } @article{MostosiSchindelinKollmannsbergeretal.2020, author = {Mostosi, Philipp and Schindelin, Hermann and Kollmannsberger, Philip and Thorn, Andrea}, title = {Haruspex: A Neural Network for the Automatic Identification of Oligonucleotides and Protein Secondary Structure in Cryo-Electron Microscopy Maps}, series = {Angewandte Chemie International Edition}, volume = {59}, journal = {Angewandte Chemie International Edition}, number = {35}, doi = {10.1002/anie.202000421}, url = {http://nbn-resolving.de/urn:nbn:de:bvb:20-opus-214763}, pages = {14788 -- 14795}, year = {2020}, abstract = {In recent years, three-dimensional density maps reconstructed from single particle images obtained by electron cryo-microscopy (cryo-EM) have reached unprecedented resolution. However, map interpretation can be challenging, in particular if the constituting structures require de-novo model building or are very mobile. Herein, we demonstrate the potential of convolutional neural networks for the annotation of cryo-EM maps: our network Haruspex has been trained on a carefully curated set of 293 experimentally derived reconstruction maps to automatically annotate RNA/DNA as well as protein secondary structure elements. It can be straightforwardly applied to newly reconstructed maps in order to support domain placement or as a starting point for main-chain placement. Due to its high recall and precision rates of 95.1 \% and 80.3 \%, respectively, on an independent test set of 122 maps, it can also be used for validation during model building. The trained network will be available as part of the CCP-EM suite.}, language = {en} } @article{HoeserKuenzer2020, author = {Hoeser, Thorsten and Kuenzer, Claudia}, title = {Object detection and image segmentation with deep learning on Earth observation data: a review-part I: evolution and recent trends}, series = {Remote Sensing}, volume = {12}, journal = {Remote Sensing}, number = {10}, issn = {2072-4292}, doi = {10.3390/rs12101667}, url = {http://nbn-resolving.de/urn:nbn:de:bvb:20-opus-205918}, year = {2020}, abstract = {Deep learning (DL) has great influence on large parts of science and increasingly established itself as an adaptive method for new challenges in the field of Earth observation (EO). Nevertheless, the entry barriers for EO researchers are high due to the dense and rapidly developing field mainly driven by advances in computer vision (CV). To lower the barriers for researchers in EO, this review gives an overview of the evolution of DL with a focus on image segmentation and object detection in convolutional neural networks (CNN). The survey starts in 2012, when a CNN set new standards in image recognition, and lasts until late 2019. Thereby, we highlight the connections between the most important CNN architectures and cornerstones coming from CV in order to alleviate the evaluation of modern DL models. Furthermore, we briefly outline the evolution of the most popular DL frameworks and provide a summary of datasets in EO. By discussing well performing DL architectures on these datasets as well as reflecting on advances made in CV and their impact on future research in EO, we narrow the gap between the reviewed, theoretical concepts from CV and practical application in EO.}, language = {en} } @article{HoeserBachoferKuenzer2020, author = {Hoeser, Thorsten and Bachofer, Felix and Kuenzer, Claudia}, title = {Object detection and image segmentation with deep learning on Earth Observation data: a review — part II: applications}, series = {Remote Sensing}, volume = {12}, journal = {Remote Sensing}, number = {18}, issn = {2072-4292}, doi = {10.3390/rs12183053}, url = {http://nbn-resolving.de/urn:nbn:de:bvb:20-opus-213152}, year = {2020}, abstract = {In Earth observation (EO), large-scale land-surface dynamics are traditionally analyzed by investigating aggregated classes. The increase in data with a very high spatial resolution enables investigations on a fine-grained feature level which can help us to better understand the dynamics of land surfaces by taking object dynamics into account. To extract fine-grained features and objects, the most popular deep-learning model for image analysis is commonly used: the convolutional neural network (CNN). In this review, we provide a comprehensive overview of the impact of deep learning on EO applications by reviewing 429 studies on image segmentation and object detection with CNNs. We extensively examine the spatial distribution of study sites, employed sensors, used datasets and CNN architectures, and give a thorough overview of applications in EO which used CNNs. Our main finding is that CNNs are in an advanced transition phase from computer vision to EO. Upon this, we argue that in the near future, investigations which analyze object dynamics with CNNs will have a significant impact on EO research. With a focus on EO applications in this Part II, we complete the methodological review provided in Part I.}, language = {en} } @article{HepbasliGredyUllrichetal.2021, author = {Hepbasli, Denis and Gredy, Sina and Ullrich, Melanie and Reigl, Amelie and Abeßer, Marco and Raabe, Thomas and Schuh, Kai}, title = {Genotype- and Age-Dependent Differences in Ultrasound Vocalizations of SPRED2 Mutant Mice Revealed by Machine Deep Learning}, series = {Brain Sciences}, volume = {11}, journal = {Brain Sciences}, number = {10}, issn = {2076-3425}, doi = {10.3390/brainsci11101365}, url = {http://nbn-resolving.de/urn:nbn:de:bvb:20-opus-248525}, year = {2021}, abstract = {Vocalization is an important part of social communication, not only for humans but also for mice. Here, we show in a mouse model that functional deficiency of Sprouty-related EVH1 domain-containing 2 (SPRED2), a protein ubiquitously expressed in the brain, causes differences in social ultrasound vocalizations (USVs), using an uncomplicated and reliable experimental setting of a short meeting of two individuals. SPRED2 mutant mice show an OCD-like behaviour, accompanied by an increased release of stress hormones from the hypothalamic-pituitary-adrenal axis, both factors probably influencing USV usage. To determine genotype-related differences in USV usage, we analyzed call rate, subtype profile, and acoustic parameters (i.e., duration, bandwidth, and mean peak frequency) in young and old SPRED2-KO mice. We recorded USVs of interacting male and female mice, and analyzed the calls with the deep-learning DeepSqueak software, which was trained to recognize and categorize the emitted USVs. Our findings provide the first classification of SPRED2-KO vs. wild-type mouse USVs using neural networks and reveal significant differences in their development and use of calls. Our results show, first, that simple experimental settings in combination with deep learning are successful at identifying genotype-dependent USV usage and, second, that SPRED2 deficiency negatively affects the vocalization usage and social communication of mice.}, language = {en} } @article{AnkenbrandLohrSchloetelburgetal.2021, author = {Ankenbrand, Markus Johannes and Lohr, David and Schl{\"o}telburg, Wiebke and Reiter, Theresa and Wech, Tobias and Schreiber, Laura Maria}, title = {Deep learning-based cardiac cine segmentation: Transfer learning application to 7T ultrahigh-field MRI}, series = {Magnetic Resonance in Medicine}, volume = {86}, journal = {Magnetic Resonance in Medicine}, number = {4}, doi = {10.1002/mrm.28822}, url = {http://nbn-resolving.de/urn:nbn:de:bvb:20-opus-257604}, pages = {2179-2191}, year = {2021}, abstract = {Purpose Artificial neural networks show promising performance in automatic segmentation of cardiac MRI. However, training requires large amounts of annotated data and generalization to different vendors, field strengths, sequence parameters, and pathologies is limited. Transfer learning addresses this challenge, but specific recommendations regarding type and amount of data required is lacking. In this study, we assess data requirements for transfer learning to experimental cardiac MRI at 7T where the segmentation task can be challenging. In addition, we provide guidelines, tools, and annotated data to enable transfer learning approaches by other researchers and clinicians. Methods A publicly available segmentation model was used to annotate a publicly available data set. This labeled data set was subsequently used to train a neural network for segmentation of left ventricle and myocardium in cardiac cine MRI. The network is used as starting point for transfer learning to 7T cine data of healthy volunteers (n = 22; 7873 images) by updating the pre-trained weights. Structured and random data subsets of different sizes were used to systematically assess data requirements for successful transfer learning. Results Inconsistencies in the publically available data set were corrected, labels created, and a neural network trained. On 7T cardiac cine images the model pre-trained on public imaging data, acquired at 1.5T and 3T, achieved DICE\(_{LV}\) = 0.835 and DICE\(_{MY}\) = 0.670. Transfer learning using 7T cine data and ImageNet weight initialization improved model performance to DICE\(_{LV}\) = 0.900 and DICE\(_{MY}\) = 0.791. Using only end-systolic and end-diastolic images reduced training data by 90\%, with no negative impact on segmentation performance (DICE\(_{LV}\) = 0.908, DICE\(_{MY}\) = 0.805). Conclusions This work demonstrates and quantifies the benefits of transfer learning for cardiac cine image segmentation. We provide practical guidelines for researchers planning transfer learning projects in cardiac MRI and make data, models, and code publicly available.}, language = {en} }