A framework is presented for unsupervised learning of representations based on infomax principle for large-scale neural populations. We use an asymptotic approximation to the Shannon's mutual information for a large neural population to demonstrate that a good initial approximation to the global information-theoretic optimum can be obtained by a hierarchical infomax method. From the initial solution, an efficient algorithm based on gradient descent of the final objective function is proposed to learn representations from the input datasets, allowing complete, overcomplete, or undercomplete bases. As confirmed by numerical experiments, our method is robust and highly efficient for extracting salient features from image datasets. Compared with the main existing methods, our algorithm has a distinct advantage in both the training speed and the robustness of unsupervised representation learning.

提出了一种基于infomax原理的框架，可实现对大规模神经群体进行无监督学习。该方法使用基于渐近的方法来对大规模神经群体的信息论下限进行计算，通过渐进性的不断往全局信息论最优解靠近的过程，可以获得一个很好的初始值。基于该初始值，提出了一个高效的算法来从输入数据集中学习特征表示，并且该方法适用于完备、过完备和欠完备情况下的基函数。和现有的方法相比，该算法在无监督表示学习的训练速度和鲁棒性方面都具有明显的优势，而且还可以轻松地扩展到用于训练深层结构网络的监督或无监督模型。

神经群体Infomax快速稳健非监督学习的信息论框架