Solving Visual Analogies Using Neural Algorithmic Reasoning (Student Abstract)
Keywords:Analogical Reasoning, Neural Algorithms, Neurosymbolic Learning
AbstractWe consider a class of visual analogical reasoning problems that involve discovering the sequence of transformations by which pairs of input/output images are related, so as to analogously transform future inputs. This program synthesis task can be easily solved via symbolic search. Using a variation of the ‘neural analogical reasoning’ approach, we instead search for a sequence of elementary neural network transformations that manipulate distributed representations derived from a symbolic space, to which input images are directly encoded. We evaluate the extent to which our ‘neural reasoning’ approach generalises for images with unseen shapes and positions.
How to Cite
Sonwane, A., Shroff, G., Vig, L., Srinivasan, A., & Dash, T. (2022). Solving Visual Analogies Using Neural Algorithmic Reasoning (Student Abstract). Proceedings of the AAAI Conference on Artificial Intelligence, 36(11), 13055-13056. https://doi.org/10.1609/aaai.v36i11.21664
AAAI Student Abstract and Poster Program