The artistic style of a painting can be sensed by the average observer, but algorithmically classifying the artistic style of an artwork is a difficult problem. The recently introduced neural-style algorithm uses features constructed from the low-level activations of a pretrained convolutional neural network to merge the artistic style of one image or set of images with the content of another. This paper investigates the effectiveness of various representations based on the neural style algorithm for use in algorithmically classifying the artistic style of paintings. This approach is compared with other neural network based approaches to artistic style classification. Results that are com-petitive with other recent work on this challenging problem are obtained.