1982年[[约翰·霍普菲尔德]]在《美国国家科学院院刊》发表论文<ref name='hopfield_1982'>{{cite journal|author=Hopfield J J.|title=Neural networks and physical systems with emergent collective computational abilities|journal=Proceedings of the National Academy of Science|year=1982|volume=79|issue=8|page=2554-2558}}</ref>,将[[自旋系统]]与[[神经网络]]结合,建立完整收敛性证明,证明对称权重网络存在[[李雅普诺夫能量函数]],迭代必然收敛至局部极小值(存储记忆)。
+
1982年[[约翰·霍普菲尔德]]在《美国国家科学院院刊》发表论文<ref name='hopfield_1982'>{{cite journal|author=Hopfield J J.|title=Neural networks and physical systems with emergent collective computational abilities|journal=Proceedings of the National Academy of Science|year=1982|volume=79|issue=8|page=2554-2558}}</ref>,将[[自旋系统]]与[[神经网络]]结合,建立完整收敛性证明,证明对称权重网络存在[[李雅普诺夫能量函数]],迭代必然收敛至局部极小值(存储记忆)。1984年霍普菲尔德拓展出'''连续Hopfield网络''',[[神经元]]取值连续,适配优化问题<ref name='hopfield_1984'>{{cite journal|author=Hopfield J J.|title=Neurons with graded response have collective computational properties like those of two-state neurons|journal=Proceedings of the National Academy of Science|year=1984|volume=81|issue=10|page=3088-3092}}</ref>