# Deep Algorithmic Question Answering: Towards a Compositionally Hybrid AI for Algorithmic Reasoning

arXiv: https://arxiv.org/abs/2109.08006 · HTML: https://mlsanity.com/paper/2109.08006/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 25 of its 46 references that are in the map.
- First posted on arXiv 16 Sep 2021.

## Builds on (most cited first, 25 of 25)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [DARTS: Differentiable Architecture Search](https://mlsanity.com/paper/1806.09055/) (2018)
- [CLEVR: A Diagnostic Dataset for Compositional Language and Elementary Visual Reasoning](https://mlsanity.com/paper/1612.06890/) (2016)
- [Neural Turing Machines](https://mlsanity.com/paper/1410.5401/) (2014)
- [Neural Probabilistic Logic Programming in DeepProbLog](https://mlsanity.com/paper/1907.08194/) (2019)
- [AutoML: A Survey of the State-of-the-Art](https://mlsanity.com/paper/1908.00709/) (2019)
- [Memory Networks](https://mlsanity.com/paper/1410.3916/) (2014)
- [A simple neural network module for relational reasoning](https://mlsanity.com/paper/1706.01427/) (2017)
- [Neural-Symbolic VQA: Disentangling Reasoning from Vision and Language Understanding](https://mlsanity.com/paper/1810.02338/) (2018)
- [Neural-Symbolic Learning and Reasoning: A Survey and Interpretation](https://mlsanity.com/paper/1711.03902/) (2017)
- [Inferring and Executing Programs for Visual Reasoning](https://mlsanity.com/paper/1705.03633/) (2017)
- [Large-scale Simple Question Answering with Memory Networks](https://mlsanity.com/paper/1506.02075/) (2015)
- [Logical Neural Networks](https://mlsanity.com/paper/2006.13155/) (2020)
- [Neural Symbolic Machines: Learning Semantic Parsers on Freebase with Weak Supervision](https://mlsanity.com/paper/1611.00020/) (2016)
- [Graph Neural Networks Meet Neural-Symbolic Computing: A Survey and Perspective](https://mlsanity.com/paper/2003.00330/) (2020)
- [Neural Algorithmic Reasoning](https://mlsanity.com/paper/2105.02761/) (2021)
- [Learning to Compose Neural Networks for Question Answering](https://mlsanity.com/paper/1601.01705/) (2016)
- [Relational recurrent neural networks](https://mlsanity.com/paper/1806.01822/) (2018)
- [Thinking Fast and Slow: Optimization Decomposition Across Timescales](https://mlsanity.com/paper/1704.07785/) (2017)
- [Neural-Symbolic Integration: A Compositional Perspective](https://mlsanity.com/paper/2010.11926/) (2020)
- [Differentiable Programs with Neural Libraries](https://mlsanity.com/paper/1611.02109/) (2016)
- [Symbolic Logic meets Machine Learning: A Brief Survey in Infinite Domains](https://mlsanity.com/paper/2006.08480/) (2020)
- [Integrating Knowledge and Reasoning in Image Understanding](https://mlsanity.com/paper/1906.09954/) (2019)

## Built on by (most cited first, 2 of 2)

- [End-to-end Algorithm Synthesis with Recurrent Networks: Logical Extrapolation Without Overthinking](https://mlsanity.com/paper/2202.05826/) (2022)
- [ALIST: Associative Logic for Inference, Storage and Transfer. A Lingua Franca for Inference on the Web](https://mlsanity.com/paper/2303.06691/) (2023)

## Abstract (arXiv)

An important aspect of artificial intelligence (AI) is the ability to reason in a step-by-step "algorithmic" manner that can be inspected and verified for its correctness. This is especially important in the domain of question answering (QA). We argue that the challenge of algorithmic reasoning in QA can be effectively tackled with a "systems" approach to AI which features a hybrid use of symbolic and sub-symbolic methods including deep neural networks. Additionally, we argue that while neural network models with end-to-end training pipelines perform well in narrow applications such as image classification and language modelling, they cannot, on their own, successfully perform algorithmic reasoning, especially if the task spans multiple domains. We discuss a few notable exceptions and point out how they are still limited when the QA problem is widened to include other intelligence-requiring tasks. However, deep learning, and machine learning in general, do play important roles as components in the reasoning process. We propose an approach to algorithm reasoning for QA, Deep Algorithmic Question Answering (DAQA), based on three desirable properties: interpretability, generalizability, and robustness which such an AI system should possess, and conclude that they are best achieved with a combination of hybrid and compositional AI.