You can not select more than 25 topics Topics must start with a chinese character,a letter or number, can include dashes ('-') and can be up to 35 characters long.

MNISTAdd.rst 742 B

12345678910111213141516171819
  1. MNIST Add
  2. ==================
  3. MNIST Add was first introduced in [1] and the inputs of this task are pairs of MNIST images and the outputs are their sums. The dataset looks like this:
  4. .. image:: ../img/image_1.jpg
  5. :width: 350px
  6. :align: center
  7. |
  8. The ``gt_pseudo_label`` is only used to test the performance of the machine learning model and is not used in the training phase.
  9. In the Abductive Learning framework, the inference process is as follows:
  10. .. image:: ../img/image_2.jpg
  11. :width: 700px
  12. [1] Robin Manhaeve, Sebastijan Dumancic, Angelika Kimmig, Thomas Demeester, and Luc De Raedt. Deepproblog: Neural probabilistic logic programming. In Advances in Neural Information Processing Systems 31 (NeurIPS), pages 3749-3759.2018.

An efficient Python toolkit for Abductive Learning (ABL), a novel paradigm that integrates machine learning and logical reasoning in a unified framework.