信号的稀疏表示或最佳n -项逼近是数据压缩、噪声抑制等众多应用中的一个重要问题。
Signal sparse representation or the optimal N-term approximation is one of the important problems, which is applied to many areas such as the data compression, denoising.
稀疏贪婪优化直接逼近目标函数的下降,因而可以明显地减小目标函数。
Sparse greedy optimization directly approximates the improvement of the objective function and thus can significantly decreases the objective function.
根据这个理论,可知稀疏或部分连接的高阶神经网络象全连接的网络一样能够逼近任意连续函数。
According to this theory, we know that partially connected higher-order neural networks can approximate any continuous functions as fully connected neural networks can do.
应用推荐