It overcomes the limitation in the assumption in other semi - supervised learning algorithms that probabilistic distribution of data is known , and has the strong ability of learning new patterns and correcting errors because of stability and plasticity of the adaptive resonance theory 在該系統(tǒng)中取消了一般半監(jiān)督學(xué)習(xí)算法中假定已知數(shù)據(jù)概率分布的條件限制,利用自適應(yīng)諧振理論的穩(wěn)定性和可塑性,使其具有非常強(qiáng)的學(xué)習(xí)新模式和糾正錯(cuò)誤能力。