The Domain Mixed Unit: A New Neural Arithmetic Layer
Fuente:
arXiv
Saved in:
| Main Author: | |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866911154883788800 |
|---|---|
| author | Curry, Paul |
| author_facet | Curry, Paul |
| contents | The Domain Mixed Unit (DMU) is a new neural arithmetic unit that learns a single parameter gate that mixes between log-space and linear-space representations while performing either addition (DMU add) or subtraction (DMU sub). Two initializations are proposed for the DMU: one covering addition and multiplication, and another covering subtraction and division. The DMU achieves state-of-the-art performance on the NALM Benchmark, a dataset designed to test the ability of neural arithmetic units to generalize arithmetic operations, specifically performing with the highest percentage solved over all seeds on multiplication and division. The DMU will be submitted as a pull request to the open-source NALM benchmark, and its code is available on GitHub at https://github.com/marict/nalm-benchmark |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_08180 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | The Domain Mixed Unit: A New Neural Arithmetic Layer Curry, Paul Machine Learning 68T07 I.2.6 The Domain Mixed Unit (DMU) is a new neural arithmetic unit that learns a single parameter gate that mixes between log-space and linear-space representations while performing either addition (DMU add) or subtraction (DMU sub). Two initializations are proposed for the DMU: one covering addition and multiplication, and another covering subtraction and division. The DMU achieves state-of-the-art performance on the NALM Benchmark, a dataset designed to test the ability of neural arithmetic units to generalize arithmetic operations, specifically performing with the highest percentage solved over all seeds on multiplication and division. The DMU will be submitted as a pull request to the open-source NALM benchmark, and its code is available on GitHub at https://github.com/marict/nalm-benchmark |
| title | The Domain Mixed Unit: A New Neural Arithmetic Layer |
| topic | Machine Learning 68T07 I.2.6 |
| url | https://arxiv.org/abs/2509.08180 |