Acceleration of Genetic Programming by Hierarchical Structure Learning: A Case Study on Image Recognition Program Synthesis

Abstract

SUMMARYWe propose a learning strategy for acceleration in learning speed of genetic programming (GP), named hierarchical structure GP (HSGP). The HSGP exploits multiple learning nodes (LNs) which are connected in a hierarchical structure, e.g., a binary tree. Each LN runs conventional evolutionary process to evolve its own population, and sends the evolved population into the connected higher-level LN. The lower-level LN evolves the population with a smaller subset of training data. The higherlevel LN then integrates the evolved population from the connected lowerlevel LNs together, and evolves the integrated population further by using a larger subset of training data. In HSGP, evolutionary processes are sequentially executed from the bottom-level LNs to the top-level LN which evolves with the entire training data. In the experiments, we adopt conventional GPs and the HSGPs to evolve image recognition programs for given training images. The results show that the use of hierarchical structure learning can significantly improve learning speed of GPs. To achieve the same performance, the HSGPs need only 30-40% of the computation cost needed by conventional GPs.

Multi-Objective Genetic Programming with Redundancy-Regulations for Automatic Construction of Image Feature Extractors

“…Many approaches exploit evolutionary computation [21], [51] techniques, especially genetic programming (GP) [13], [33], to search for the optimal programs. Some research efforts have attempted to construct a part of object recognition programs, e.g., feature extractor [19], [20], [25], [42], [48], [50], edge detector [49] or interest point detector [22], [23], [26], while some researchers focus on construction of complete object recognition programs [5], [28], [34], [35], [38]. Also various image processing tasks have been studied, e.g., classification [19], [20], segmentation [31], [32], [35], [44], image retrieval [2], or texture analysis [4].…”