Unsupervised learning of hidden representations has been one of the most vibrant research directions in machine learning in recent years. In this work we study the brain-like Bayesian Confidence Propagating Neural Network (BCPNN) model, recently extended to extract sparse distributed high-dimensional representations. The usefulness and class-dependent separability of the hidden representations when trained on MNIST and Fashion-MNIST datasets is studied using an external linear classifier and compared with other unsupervised learning methods that include restricted Boltzmann machines and autoencoders.
翻译:近年来,在机器学习方面最有活力的研究方向之一是在不受监督的情况下学习隐蔽的表示方式。 在这项工作中,我们研究了像Bayesian Infusure propagate NealNetwork(BCPNN)这样的大脑型神经网络(BCPNN ) 模型,该模型最近被扩展,以提取分散的分散式高维表示方式。 在对MNIST和时装MNIST数据集进行训练时,隐蔽的表示方式的有用性和阶级分离性正在使用外部线性分类器进行研究,并与其他不受监督的学习方法(包括限制的Boltzmann机器和自动编码器)进行比较。