The importance of analogy-making and analogy-based reasoning for human cognition and learning by now has widely been recognized, and analogy-based methods are slowly also being explicitly integrated into the canon of approved education and teaching techniques. Still, the actual level of knowledge about analogy as instructional means and device as of today is rather low and subject to scientific study and investigation. In this paper, we propose the fruitful use of computational analogy-engines as methodological tool in this domain of research, motivating our claim by a short case study showing how Heuristic-Driven Theory Projection can be used to model the mode of operation of an analogy taken from a science class for 8 to 9 year old children.
In this paper, we study the problem of answering visual analogy questions. These questions take the form of image A is to image B as image C is to what. Answering these questions entails discovering the mapping from image A to image B and then extending the mapping to image C and searching for the image D such that the relation from A to B holds for C to D. We pose this problem as learning an embedding that encourages pairs of analogous images with similar transformations to be close together using convolutional neural networks with a quadruple Siamese architecture. We introduce a dataset of visual analogy questions in natural images, and show first results of its kind on solving analogy questions on natural images.