Meta-Learning in Computational Intelligence

• Συγγραφή απο Οργανισμό/Αρχή: SpringerLink (Online service)
• Άλλοι συγγραφείς: Jankowski, Norbert (Επιμελητής έκδοσης), Duch, Włodzisław (Επιμελητής έκδοσης), Gra̧bczewski, Krzysztof (Επιμελητής έκδοσης)
• Μορφή: Ηλεκτρονική πηγή Ηλ. βιβλίο
• Γλώσσα: English
• Έκδοση: Berlin, Heidelberg : Springer Berlin Heidelberg, 2011.
• Σειρά: Studies in Computational Intelligence, 358
• Θέματα: Engineering.; Artificial intelligence.; Computational intelligence.; Computational Intelligence.; Artificial Intelligence (incl. Robotics).

Computational Intelligence (CI) community has developed hundreds of algorithms for intelligent data analysis, but still many hard problems in computer vision, signal processing or text and multimedia understanding, problems that require deep learning techniques, are open. Modern data mining packages...

Πίνακας περιεχομένων:

• Universal meta-learning architecture and algorithms
• Meta-learning of instance selection for data summarization
• Choosing the metric: a simple model approach
• Meta-learning Architectures: Collecting, Organizing and Exploiting Meta-knowledge
• Computational intelligence for meta-learning: a promising avenue of research
• Self-organization of supervised models
• Selecting Machine Learning Algorithms Using the Ranking Meta-Learning Approach
• A Meta-Model Perspective and Attribute Grammar Approach to Facilitating the Development of Novel Neural Network Models
• Ontology-Based Meta-Mining of Knowledge Discovery Workflows
• Optimal Support Features for Meta-learning.