Compiled from the post-proceedings of the 13th Italian Workshop on Neural Nets, this book contains 21 revised full papers and three invited papers. They are organized in topical sections on architectures and algorithms, image and signal processing applications, and learning in neural networks.

Review Papers.- Ensembles of Learning Machines.- Eduardo R. Caianiello Lecture.- Learning Preference Relations from Data.- Francesco E. Lauria Lecture.- Increasing the Biological Inspiration of Neural Networks.- Architectures and Algorithms.- Hybrid Automatic Trading Systems: Technical Analysis & Group Method of Data Handling.- Interval TOPSIS for Multicriteria Decision Making.- A Distributed Algorithm for Max Independent Set Problem Based on Hopfield Networks.- Extended Random Neural Networks.- Generalized Independent Component Analysis as Density Estimation.- Spline Recurrent Neural Networks for Quad-Tree Video Coding.- MLP Neural Network Implementation on a SIMD Architecture.- Image and Signal Processing.- A New Approach to Detection of Muscle Activation by Independent Component Analysis and Wavelet Transform.- Learning to Balance Upright Posture: What can be Learnt Using Adaptive NN Models?.- Detection of Facial Features.- A Two Stage Neural Architecture for Segmentation and Superquadrics Recovery from Range Data.- Automatic Discrimination of Earthquakes and False Events in Seismological Recording for Volcanic Monitoring.- A Comparison of Signal Compression Methods by Sparse Solution of Linear Systems.- Fuzzy Time Series for Forecasting Pollutants Concentration in the Air.- Real-Time Perceptual Coding of Wideband Speech by Competitive Neural Networks.- Sound Synthesis by Flexible Activation Function Recurrent Neural Networks.- Special Session on “Learning in Neural Networks: Limitations and Future Trends” Chaired by Marco Gori.- Mathematical Modelling of Generalization.- Structural Complexity and Neural Networks.- Bayesian Learning Techniques: Application to Neural Networks with Constraints on Weight Space.- A Short Review of Statistical Learning Theory.-Increasing the Biological Inspiration of Neural Networks.