IEEE Trans Cybern. 2022 May;52(5):3221-3231. doi: 10.1109/TCYB.2020.3009582. Epub 2022 May 19.
In this article, an adaptive learning framework is established for a deep weighted sparse autoencoder (AE) by resorting to the multiobjective evolutionary algorithm (MOEA). The weighted sparsity is introduced to facilitate the design of the varying degrees of the sparsity constraints imposed on the hidden units of the AE. The MOEA is exploited to adaptively seek appropriate hyperparameters, where the divide-and-conquer strategy is implemented to enhance the MOEA's performance in the context of deep neural networks. Moreover, a sharing scheme is proposed to further reduce the time complexity of the learning process at the slight expense of the learning precision. It is shown via extensive experiments that the established adaptive learning framework is effective, where different sparse models are utilized to demonstrate the generality of the proposed results. Then, the generality of the proposed framework is examined on the convolutional AE and VGG-16 network. Finally, the developed framework is applied to the blind image quantity assessment that illustrates the applicability of the established algorithms.
本文通过多目标进化算法 (MOEA) 为深度加权稀疏自动编码器 (AE) 建立了一个自适应学习框架。引入加权稀疏性有助于设计对 AE 的隐藏单元施加的不同程度的稀疏性约束。利用 MOEA 自适应地寻找合适的超参数，其中实施分而治之策略以提高 MOEA 在深度神经网络环境中的性能。此外，还提出了一种共享方案，以进一步降低学习过程的时间复杂度，而学习精度的损失可以忽略不计。通过广泛的实验表明，所建立的自适应学习框架是有效的，其中利用不同的稀疏模型来证明所提出结果的通用性。然后，在所提出的框架上检查卷积 AE 和 VGG-16 网络的通用性。最后，将开发的框架应用于盲图像数量评估，说明了所建立算法的适用性。
