Applying Genetic Algorithms to Neural Network Optimization

这项工作将使用遗传算法来解决两类 与神经网络相关的优化问题：（1） 递归和前馈神经网络中的权值优化 神经网络的连通性优化 网络. 建立具有挑战性的衡量标准 成功后，它将建立和测试大型雷达信号网络 脉冲检测 使用遗传算法定义 神经网络连接已经成为一个研究领域 只在去年。 遗传算法已被用于 针对小问题优化网络连接性，生成网络 它比标准的“全连接”网络学习得快得多， 在数据数量上惊人地一致 学习所需的演示文稿。 这项工作将扩大 目前的做法，结合遗传算法的代码， 重量优化与我们目前的方法， 优化连通性。 这种组合应该允许 大规模同时优化连接性和权重 问题 最后，成功地优化了前馈 使用遗传算法的网络是重要的，因为这些 算法不假设权重（参数） 遗传算法要评估的 采用 应该可以应用遗传算法 直接针对经常性的网络优化问题， 具有限制性的存储和计算要求， 使用真正的梯度下降学习技术进行训练。

This work will use genetic algorithms to solve two classes of optimization problems related to neural networks: (1) the optimization of weights in recurrent and feed forward neural networks and (2) the optimization of the connectivity of neural networks. To establish a challenging criteria for measuring success, it will build and test large networks for radar signal pulse detection. The use of genetic algorithms for defining neural network connectivity has emerged as an area of research only in the last year. A genetic algorithm has been used to fefine network connectivities for small problems, producing nets which learn much faster than standard "fully-connected" nets and which are suprisingly consistent in the number of data presentations required for learning. This work will extend the current approach by combining the genetic algorithm code for weight optimization with a variation on our current approach to optimizing the connectivity. This combination should allow optimization of connectivity and weights simultaneously on large problems. Finally, the successful optimization of feed forward networks using genetic algorithms is significant because these algorithms make no assumptions about how the weights (parameters) that the genetic algorithm is asked to evaluate are actually used. It should be possible to applied the genetic algorithms directly to recurrent network optimization problems which tend to have restrictive storage and computational requirements when trained with true gradient descent learning techniques.