Artificial Neural Networks and Machine Learning – ICANN 2020 29th International Conference on Artificial Neural Networks, Bratislava, Slovakia, September 15–18, 2020, Proceedings, Part I

The total of 139 full papers presented in these proceedings was carefully reviewed and selected from 249 submissions. They were organized in 2 volumes focusing on topics such as adversarial machine learning, bioinformatics and biosignal analysis, cognitive models, neural network theory and information theoretic learning, and robotics and neural models of perception and action.

*The conference was postponed to 2021 due to the COVID-19 pandemic.

Adversarial Machine Learning.- On the security relevance of initial weights in deep neural networks.- Fractal Residual Network for Face Image Super-Resolution.- From Imbalanced Classification to Supervised Outlier Detection Problems: Adversarially Trained Auto Encoders.- Generating Adversarial Texts for Recurrent Neural Networks.- Enforcing Linearity in DNN succours Robustness and Adversarial Image Generation.- Computational Analysis of Robustness in Neural Network Classifiers.- Bioinformatics and Biosignal Analysis.- Convolutional neural networks with reusable full-dimension-long layers for feature selection and classification of motor imagery in EEG signals.- Compressing Genomic Sequences by Using Deep Learning.- Learning Tn5 sequence bias from ATAC-seq on naked chromatin.- Tucker tensor decomposition of multi-session EEG data.- Reactive Hand Movements from Arm Kinematics and EMG Signals Based on Hierarchical Gaussian Process Dynamical Models.- Cognitive Models.- Investigating Efficient Learning and Compositionality in Generative LSTM Networks.- Fostering Event Compression using Gated Surprise.- Physiologically-inspired Neural Circuits for the Recognition of Dynamic Faces.- Hierarchical Modeling with Neurodynamical Agglomerative Analysis.- Convolutional Neural Networks and Kernel Methods.- Deep and Wide Neural Networks Covariance Estimation.- Monotone deep Spectrum Kernels.- Permutation Learning in Convolutional Neural Networks for Time Series Analysis.- Deep Learning Applications I.- GTFNet: Ground Truth Fitting Network for Crowd Counting.- Evaluation of Deep Learning Methods for Bone Suppression from Dual Energy Chest Radiography.- Multi-Person Absolute 3D Human Pose Estimation with Weak Depth Supervision.- Solar Power Forecasting Based on Pattern Sequence Similarity and Meta-Learning.- Analysis and Prediction of Deforming 3D Shapes using Oriented Bounding Boxes and LSTM Autoencoders.- Deep Learning Applications II.-Novel Sketch-based 3D Model Retrieval via Cross-domain Feature Clustering and Matching.- Multi-objective Cuckoo Algorithm for Mobile Devices Network Architecture Search.- DeepED: a Deep Learning Framework for Estimating Evolutionary Distances.- Interpretable Machine Learning Structure for an Early Prediction of Lane Changes.- Explainable Methods.- Convex Density Constraints for Computing Plausible Counterfactual Explanations.- Identifying Critical States by the Action-Based Variance of Expected Return.- Explaining Concept Drift by Means of Direction.- Few-shot Learning.- Context Adaptive Metric Model for Meta-Learning.- Ensemble-Based Deep Metric Learning for Few-Shot Learning.- More Attentional Local Descriptors for Few-shot Learning.- Implementation of Siamese-based Few-shot Learning Algorithms for the Distinction of COPD and Asthma Subjects.- Few-Shot Learning for Medical Image Classification.- Generative Adversarial Network.- Adversarial Defense via Attention-based Randomized Smoothing.- Learning to Learn from Mistakes: Robust Optimization for Adversarial Noise.- Unsupervised Anomaly Detection with a GAN Augmented Autoencoder.- An Efficient Blurring-Reconstruction Model to Defend against Adversarial Attacks.- EdgeAugment: Data Augmentation by Fusing and Filling Edge Map.- Face Anti-spoofing with a Noise-Attention Network Using Color-Channel Difference Images.- Generative and Graph Models.- Variational Autoencoder with Global- and Medium Timescale Auxiliaries for Emotion Recognition from Speech.- Improved Classification Based on Deep Belief Networks.- Temporal Anomaly Detection by Deep Generative Models with Applications to Biological Data.- Inferring, Predicting, and Denoising Causal Wave Dynamics.- PART-GAN: Privacy-Preserving Time-Series Sharing.- EvoNet: A Neural Network for Predicting the Evolution of Dynamic Graphs.- Hybrid Neural-symbolic Architectures.- Facial Expression Recognition Method based on a Part-based TemporalConvolutional Network with a Graph-Structured Representation.- Generating Facial Expressions Associated with Text.- Image Processing.- Bilinear Fusion of Commonsense Knowledge with Attention-Based NLI Models.- Neural-Symbolic Relational Reasoning on Graph Models: Effective Link Inference and Computation from Knowledge Bases.- Tell Me Why You Feel That Way: Processing Compositional Dependency for Tree-LSTM Aspect Sentiment Triplet Extraction (TASTE).- SOM-based System for Sequence Chunking and Planning.- Bilinear Models for Machine Learning.- Enriched Feature Representation and Combination for Deep Saliency Detection.- Spectral Graph Reasoning Network for Hyperspectral Image Classification.- Salient Object Detection with Edge Recalibration.- Multi-Scale Cross-Modal Spatial Attention Fusion for Multi-label Image Recognition.- A New Efficient Finger-Vein Verification Based on Lightweight Neural Network Using Multiple Schemes.- Medical Image Processing.- SU-Net: An EfficientEncoder-Decoder Model of Federated Learning for Brain Tumor Segmentation.- Synthesis of Registered Multimodal  Medical Images with Lesions.- ACE-Net: Adaptive Context Extraction Network for Medical Image Segmentation.- Wavelet U-Net for Medical Image Segmentation.- Recurrent Neural Networks.- Character-based LSTM-CRF with semantic features for Chinese Event Element Recognition.- Sequence Prediction using Spectral RNNs.- Attention Based Mechanism for Energy Load Time Series Forecasting: AN-LSTM.- DartsReNet: Exploring new RNN cells in ReNet architectures.- On Multi-modal Fusion for Freehand Gesture Recognition.- Recurrent Neural Network Learning of Performance and Intrinsic Population Dynamics from Sparse Neural Data.