Solving Visual Analogies Using Neural Algorithmic Reasoning (Student Abstract)


  • Atharv Sonwane BITS Pilani
  • Gautam Shroff TCS Research
  • Lovekesh Vig TCS Research
  • Ashwin Srinivasan BITS Pilani
  • Tirtharaj Dash BITS Pilani



Analogical Reasoning, Neural Algorithms, Neurosymbolic Learning


We 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.