Genetic Programming: 25th European Conference, Eurogp 2022, Held as Part of Evostar 2022, Madrid, Spain, April 20-22, 2022, Proceedings

ISBN-13: 9783031020551 / Angielski / Miękka / 2022

Medvet, Eric

Opis

This book constitutes the refereed proceedings of the 25th European Conference on Genetic Programming, EuroGP 2022, held as part of Evo*2021, as Virtual Event, in April 2022, co-located with the Evo*2022 events, EvoCOP, EvoMUSART, and EvoApplications. The 12 revised full papers and 7 short papers presented in this book were carefully reviewed and selected from 35 submissions. The wide range of topics in this volume reflects the current state of research in the field. The collection of papers cover topics including developing new operators for variants of GP algorithms, as well as exploring GP applications to the optimization of machine learning methods and the evolution of complex combinational logic circuits. 

Spis treści

Long Presentations.- Evolving Adaptive Neural Network Optimizers for Image Classification.- Combining Geometric Semantic GP with Gradient-descent Optimization.- One-Shot Learning of Ensembles of Temporal Logic Formulas for Anomaly Detection in Cyber-Physical Systems.- Multi-objective GP with AWS for Symbolic Regression.- SLUG: Feature Selection Using Genetic Algorithms and Genetic Programming.- Evolutionary Design of Reduced Precision Levodopa-Induced Dyskinesia Classifiers.- Using Denoising Autoencoder Genetic Programming to Control Exploration and Exploitation in Search.- Program Synthesis with Genetic Programming: The Influence of Batch Sizes.- Genetic Programming-Based Inverse Kinematics for Robotic Manipulators.- On the Schedule for Morphological Development of Evolved Modular Soft Robots.- An Investigation of Multitask Linear Genetic Programming for Dynamic Job Shop Scheduling.- Cooperative Co-Evolution and Adaptive Team Composition for a Multi-Rover Resources Allocation Problem.- Short Presentations.-  Synthesizing Programs from Program Pieces using Genetic Programming and Refinement Type Checking.- Creating Diverse Ensembles for Classification with Genetic Programming and Neuro-MAP-Elites.- Evolving Monotone Conjunctions in Regimes Beyond Proved Convergence.- Accurate and Interpretable Representations of Environments with Anticipatory Learning Classifier Systems.- Exploiting Knowledge from Code to Guide Program Search.- Multi-Objective Genetic Programming for Explainable Reinforcement Learning.- Permutation-Invariant Representation of Neural Networks with Neuron Embeddings.