Secondly, the complexity of fully-connected kernel auto-associative memory models is reduced.
对全互连的核自联想记忆模型框架进行了稀疏化改造。
On the basis of aforesaid work, the author further proposes robust face recognition algorithms based on sparse kernel auto - associative memory models.
在上述工作的基础上，本文主要研究了基于小世界体系的指数核自联想记忆模型在人脸识别中的应用。
Fuzzy inference network (FIN) and fuzzy associative memory network (FAM) are two most important FNN models.
模糊推理网络(FIN)和模糊联想记忆网络(FAM)是两种最重要的FNN模型。
Finally, computer simulations demonstrate that the constructed models have good performance on many-to-many associative memory.
最后的计算机模拟，证实了新的模型具有良好的多对多联想记忆功能。
Finally, we apply neural network models with dynamic depressing synapses in the field of associative memory.
最后对抑制型动态突触神经网络在联想记忆中的应用进行了研究。
The models used in this work were from linear associative memory method and fast compensated by adaptively learning from the given facial data, which were obtained in same condition as testing.
该方法在真实识别前，通过用与真实识别相同的环境条件下所获得的人脸图像数据对原始模型进行更新补偿，实现了模型自适应。
The models used in this work were from linear associative memory method and fast compensated by adaptively learning from the given facial data, which were obtained in same condition as testing.
该方法在真实识别前，通过用与真实识别相同的环境条件下所获得的人脸图像数据对原始模型进行更新补偿，实现了模型自适应。
应用推荐