Neural algorithmic reasoning
By Petar Velickovic, Charles Blundell. 2021
142 citations recorded by the source corpus.
We present neural algorithmic reasoning—the art of building neural networks that are able to execute algorithmic computation—and provide our opinion on its transformative potential for running classical algorithms on inputs previously considered inaccessible to them.
Subfields: Artificial Intelligence, Computer Networks and Communications
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Artificial Intelligence
- Yejin Choi
- Mohit Bansal
- Hannaneh Hajishirzi
- Xiang Ren
- Luke S. Zettlemoyer
- Percy Liang
- Sean Welleck
- Yoshua Bengio
In Computer Networks and Communications
- Yejin Choi
- Zaïd Harchaoui
- Aaron C. Courville
- Hugo Larochelle
- Chandra Bhagavatula
- Melanie Sclar
- Sean Welleck
- Behnam Neyshabur
Citations in the corpus
- Show Your Work: Scratchpads for Intermediate Computation with Language Models (2021, neutral): “Neural networks that accurately represent the semantics of programs could enable a variety of downstream tasks, including program synthesis (Devlin et al., 2017), program analysis (Allamanis et al., 2018), and other algorithmic reasoning tasks (Velickovic & Blundell, 2021).”
- Faith and Fate: Limits of Transformers on Compositionality (2023, background): “However, these models have also been shown to struggle across multiple domains [32], including algorithmic reasoning [78], commonsense reasoning [62, 40], theory of mind [65], planning [76], logical reasoning [70], and ethical reasoning [36].”
- Teaching Algorithmic Reasoning via In-context Learning (2022, methodology): “We refer to this behavior as algorithmic reasoning (Kaiser and Sutskever, 2015; Veliˇckovi´c and Blundell, 2021).”