Summary of Dolphin: a Programmable Framework For Scalable Neurosymbolic Learning, by Aaditya Naik et al.
Dolphin: A Programmable Framework for Scalable Neurosymbolic Learning
by Aaditya Naik, Jason Liu, Claire Wang, Amish Sethi, Saikat Dutta, Mayur Naik, Eric Wong
First submitted to arxiv on: 4 Oct 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: None
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary This paper presents a framework called Dolphin that addresses challenges in scaling neurosymbolic learning to complex symbolic programs, large datasets, or both. Neurosymbolic learning combines symbolic reasoning with deep learning, but existing frameworks face difficulties in executing complex symbolic reasoning and vectorizing probabilistic computations. The authors introduce Dolphin, which supports neurosymbolic programs in Python and executes complex symbolic reasoning on the CPU while vectorizing probabilistic computations and gradient propagation on the GPU. Across 13 benchmarks spanning tasks over text, image, and video data, with features like recursion and black-box functions, Dolphin achieves state-of-the-art accuracies on more complex benchmarks while existing frameworks fail to converge within the time limit. On simpler benchmarks, Dolphin matches their performance, achieving results 1.71x to 62x faster than baselines. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This paper introduces a new way of combining artificial intelligence (AI) with human reasoning called neurosymbolic learning. Existing methods have trouble handling complex problems or large amounts of data. The researchers created a framework called Dolphin that makes it easier to solve these complex problems by using both AI and human reasoning. They tested Dolphin on 13 different tasks, such as recognizing text, images, and videos, and found that it worked better than other methods in many cases. Dolphin was able to get the right answers faster than other methods, too. |
Keywords
* Artificial intelligence * Deep learning
