Relational program synthesis with numerical reasoning
Learning programs with numerical values is fundamental to many AI applications, including bio-informatics and drug design. However, current program synthesis approaches struggle to learn programs with numerical values. An especially difficult problem is learning continuous values from multiple examp...
| Main Authors: | , |
|---|---|
| Format: | Conference item |
| Language: | English |
| Published: |
Association for the Advancement of Artificial Intelligence
2023
|
| _version_ | 1797110176472367104 |
|---|---|
| author | Hocquette, C Cropper, A |
| author_facet | Hocquette, C Cropper, A |
| author_sort | Hocquette, C |
| collection | OXFORD |
| description | Learning programs with numerical values is fundamental to many AI applications, including bio-informatics and drug design. However, current program synthesis approaches struggle to learn programs with numerical values. An especially difficult problem is learning continuous values from multiple examples, such as intervals. To overcome this limitation, we introduce an inductive logic programming approach which combines relational learning with numerical reasoning. Our approach, which we call NumSynth, uses satisfiability modulo theories solvers to efficiently learn programs with numerical values. Our approach can identify numerical values in linear arithmetic fragments, such as real difference logic, and from infinite domains, such as real numbers or integers. Our experiments on four diverse domains, including game playing and program synthesis, show that our approach can (i) learn programs with numerical values from linear arithmetical reasoning, and (ii) outperform existing approaches in terms of predictive accuracies and learning times. |
| first_indexed | 2024-03-07T07:51:48Z |
| format | Conference item |
| id | oxford-uuid:71016e97-bcd2-4e79-b4aa-d38af237a730 |
| institution | University of Oxford |
| language | English |
| last_indexed | 2024-03-07T07:51:48Z |
| publishDate | 2023 |
| publisher | Association for the Advancement of Artificial Intelligence |
| record_format | dspace |
| spelling | oxford-uuid:71016e97-bcd2-4e79-b4aa-d38af237a7302023-07-21T10:47:59ZRelational program synthesis with numerical reasoningConference itemhttp://purl.org/coar/resource_type/c_5794uuid:71016e97-bcd2-4e79-b4aa-d38af237a730EnglishSymplectic ElementsAssociation for the Advancement of Artificial Intelligence2023Hocquette, CCropper, ALearning programs with numerical values is fundamental to many AI applications, including bio-informatics and drug design. However, current program synthesis approaches struggle to learn programs with numerical values. An especially difficult problem is learning continuous values from multiple examples, such as intervals. To overcome this limitation, we introduce an inductive logic programming approach which combines relational learning with numerical reasoning. Our approach, which we call NumSynth, uses satisfiability modulo theories solvers to efficiently learn programs with numerical values. Our approach can identify numerical values in linear arithmetic fragments, such as real difference logic, and from infinite domains, such as real numbers or integers. Our experiments on four diverse domains, including game playing and program synthesis, show that our approach can (i) learn programs with numerical values from linear arithmetical reasoning, and (ii) outperform existing approaches in terms of predictive accuracies and learning times. |
| spellingShingle | Hocquette, C Cropper, A Relational program synthesis with numerical reasoning |
| title | Relational program synthesis with numerical reasoning |
| title_full | Relational program synthesis with numerical reasoning |
| title_fullStr | Relational program synthesis with numerical reasoning |
| title_full_unstemmed | Relational program synthesis with numerical reasoning |
| title_short | Relational program synthesis with numerical reasoning |
| title_sort | relational program synthesis with numerical reasoning |
| work_keys_str_mv | AT hocquettec relationalprogramsynthesiswithnumericalreasoning AT croppera relationalprogramsynthesiswithnumericalreasoning |