# Naive Few-Shot Learning: Uncovering the fluid intelligence of machines

arXiv: https://arxiv.org/abs/2205.12013 · HTML: https://mlsanity.com/paper/2205.12013/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 17 of its 33 references that are in the map.
- First posted on arXiv 24 May 2022.

## Builds on (most cited first, 17 of 17)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [Representation Learning with Contrastive Predictive Coding](https://mlsanity.com/paper/1807.03748/) (2018)
- [Densely Connected Convolutional Networks](https://mlsanity.com/paper/1608.06993/) (2016)
- [Learning to Compare: Relation Network for Few-Shot Learning](https://mlsanity.com/paper/1711.06025/) (2017)
- [Learning to Generalize: Meta-Learning for Domain Generalization](https://mlsanity.com/paper/1710.03463/) (2017)
- [Data-Efficient Image Recognition with Contrastive Predictive Coding](https://mlsanity.com/paper/1905.09272/) (2019)
- [Do Deep Generative Models Know What They Don't Know?](https://mlsanity.com/paper/1810.09136/) (2018)
- [A simple neural network module for relational reasoning](https://mlsanity.com/paper/1706.01427/) (2017)
- [Measuring abstract reasoning in neural networks](https://mlsanity.com/paper/1807.04225/) (2018)
- [Meta-Learning without Memorization](https://mlsanity.com/paper/1912.03820/) (2019)
- [Self-trained Deep Ordinal Regression for End-to-End Video Anomaly Detection](https://mlsanity.com/paper/2003.06780/) (2020)
- [Meta-Learning Requires Meta-Augmentation](https://mlsanity.com/paper/2007.05549/) (2020)
- [Unsupervised Detection of Anomalous Sound based on Deep Learning and the Neyman-Pearson Lemma](https://mlsanity.com/paper/1810.09133/) (2018)
- [Few-shot Visual Reasoning with Meta-analogical Contrastive Learning](https://mlsanity.com/paper/2007.12020/) (2020)
- [Solving Raven's Progressive Matrices with Neural Networks](https://mlsanity.com/paper/2002.01646/) (2020)

## Built on by (most cited first, 1 of 1)

- [Two pathways to resolve relational inconsistencies](https://mlsanity.com/paper/2411.05809/) (2024)

## Abstract (arXiv)

In this paper, we aimed to help bridge the gap between human fluid intelligence - the ability to solve novel tasks without prior training - and the performance of deep neural networks, which typically require extensive prior training. An essential cognitive component for solving intelligence tests, which in humans are used to measure fluid intelligence, is the ability to identify regularities in sequences. This motivated us to construct a benchmark task, which we term textitsequence consistency evaluation (SCE), whose solution requires the ability to identify regularities in sequences. Given the proven capabilities of deep networks, their ability to solve such tasks after extensive training is expected. Surprisingly, however, we show that naive (randomly initialized) deep learning models that are trained on a textitsingle SCE with a textitsingle optimization step can still solve non-trivial versions of the task relatively well. We extend our findings to solve, without any prior training, real-world anomaly detection tasks in the visual and auditory modalities. These results demonstrate the fluid-intelligent computational capabilities of deep networks. We discuss the implications of our work for constructing fluid-intelligent machines.