给出一种快速感知器学习算法--变步长感 知器学习算法,这种学习算法依公式W(k+1)=W(k)-2W(k)XTkX(k)调整权值和阈值。定理表明这种算法 必然在有限步内收敛。%In this paper a new learning algorithm of perception with variable paces is given which adjusts its weights and threshold values according to the following formula:W(k+1)=W(k)-2W(k)XTkX(k). A theorem shows that the algorithm must be convergente after finite steps.
展开▼