ANN_IntroductiontoANN讲义.pptVIP

Learning Rules Supervised learning Reinforcement learning Unsupervised learning Supervised Learning Learning with a teacher Learning by examples ? Training set Supervised Learning x Error signal Generator d y ANN W Reinforcement Learning Learning with a critic Learning by comments Reinforcement Learning x Critic signal Generator y ANN W Reinforcement Signal Unsupervised Learning Self-organizing Clustering Form proper clusters by discovering the similarities and dissimilarities among objects. Unsupervised Learning x y ANN W The General Weight Learning Rule Input: Output: ?i . . . . . . wi1 wi2 wij wi,m-1 x1 x2 xj xm-1 yi ?i The General Weight Learning Rule Input: Output: ?i . . . . . . wi1 wi2 wij wi,m-1 x1 x2 xj xm-1 yi ?i We want to learn the weights bias. We want to learn the weights bias. The General Weight Learning Rule Input: ?i . . . . . . wi1 wi2 wij wi,m-1 x1 x2 xj xm-1 ?i Let xm = ?1 and wim = ?i. The General Weight Learning Rule Input: ?i . . . . . . wi1 wi2 wij wi,m-1 x1 x2 xj xm-1 Let xm = ?1 and wim = ?i. xm= ?1 wim=?i The General Weight Learning Rule Input: ?i . . . . . . wi1 wi2 wij wi,m-1 x1 x2 xj xm-1 xm= ?1 wim=?i yi wi=(wi1, wi2 ,…,wim)T ?wi(t) = ? We want to learn The General Weight Learning Rule wi x yi r di Learning Signal Generator The General Weight Learning Rule wi x yi r di Learning Signal Generator The General Weight Learning Rule wi x yi r di Learning Signal Generator The General Weight Learning Rule wi x yi r di Learning Signal Generator ? Learning Rate The General Weight Learning Rule wi=(wi1, wi2 ,…,wim)T We want to learn Discrete-Time Weight Modification Rule: Continuous-Time Weight Modification Rule: * 旅行商问题，即TSP问题（Travelling Salesman Problem）是数学领域中著名问题之一。假设有一个旅行商人要拜访n个城市，他必须选择所要走的路径，路经的限制是每个城市只能拜访一次，而且最后要回到原来出发的城市。路径的选择目标是要求得的路径路程为所有路径之中的最小值。 * 如，在一方阵中含几千个光敏单元的VLSI芯片，它是以人的 视网膜中锥体细胞的方式来连接一块VLSI芯片． * 1、在圣地雅哥召开了， 1987年首届国际神经网络大会；创办Journal Neural Networks，十几种国际著名的神经网络学术刊物相继问世。 2、美国国防部高级预研计划局(DARPA)组织了一批专家、教授进行调研，走访了三千多位有关 研究者和著