Neural Networks and Their Applications -- A fast learning algorithm for the multilayer neural network -- A new computational approach to the Levenberg-Marquardt learning algorithm -- Training subjective perception biased images of vehicle ambient lights with deep belief networks using backpropagation- and enforcing-rules supervised -- An Empirical Study of Adversarial Domain Adaptation on Time Series Data -- Human-AI-Collaboration to increase the perception of VR -- Portfolio Transformer for Attention-Based Asset Allocation -- Transfer Learning with Deep Neural Embeddings for Music Classification Tasks -- Analysis and detection of DDoS Backscatter using NetFlow data, hyperband-optimised DeepLearning and explainability techniques -- BiLSTM deep learning model for heart problems detection -- Short Texts Representations for Legal Domain Classification -- Synthetic slowness shear well-logs prediction using supervised machine learning models -- ARIMA for Short-Term and LSTM for Long-Term in Daily Bitcoin Price Prediction -- Multi-objective Bayesian Optimization for Neural Architecture Search -- Multilayer Perceptrons with Banach-like Perceptrons Based on Semi-Inner Products - About Approximation Completeness -- Fuzzy Systems and Their Applications -- Similarity Fuzzy Semantic Networks and Inference. An application to analysis of radical discourse in Twitter -- An Application of Information Granules to Detect Anomalies in COVID-19 Reports -- Type-2 fuzzy classifier with smooth type-reduction -- Evolutionary Algorithms and Their Applications -- A multi-population-based algorithm with different ways of subpopulations cooperation -- Automated Design of Dynamic Heuristic Set Selection for Cross-Domain Selection Hyper-Heuristics -- Evolutionary Approach to Melodic Line Harmonization -- Using Automatic Programming toImprove Gradient Boosting for Classification -- Forced Movement Extensions of the Particle Swarm Optimizers with Inertia Weight -- LQ-R-SHADE: R-SHADE with quadratic surrogate model -- Pattern Classification -- Overload Monitoring System Using Sound Analysis for Electrical Machines -- Employing Convolutional Neural Networks for Continual Learning -- Explaining Machine Learning Predictions In Botnet Detection -- Learning Functional Descriptors Based on the Bernstein Polynomials - Preliminary Studies -- Artificial Intelligence in Modeling and Simulation -- Multiscale Multifractal Detrended Analysis of Speculative Attacks Dynamics in Cryptocurrencies -- A Heuristic Repair Algorithm for the Hospitals/Residents problem with Ties -- The Impact of Data Preprocessing on Prediction Effectiveness -- Convergence of RBF Networks Regression Function Estimates and Classifiers -- A Comparative Study of Genetic Programming Variants -- Optimization of Parameterized Behavior Trees in RTS Games -- Using Answer Set Programming to Improve Sensor Network Lifetime -- Spectroscopy-Based Prediction of In Vitro Dissolution Profile Using Random Decision Forests -- Validation of Labelling Algorithms for Abstract Argumentation Frameworks: The Case of Listing Stable Extensions.

The two-volume set LNAI 13588 and 13589 constitutes the refereed post-conference proceedings of the 21st International Conference on Artificial Intelligence and Soft Computing, ICAISC 2022, held in Zakopane, Poland, during June 19-23, 2022. The 69 revised full papers presented in these proceedings were carefully reviewed and selected from 161 submissions. The papers are organized in the following topical sections: Volume I: Neural networks and their applications; fuzzy systems and their applications; evolutionary algorithms and their applications; pattern classification; artificial intelligence in modeling and simulation. Volume II: Computer vision, image and speech analysis; data mining; various problems of artificial intelligence; bioinformatics, biometrics and medical applications.