# Convolutional Neural Networks Trained to Identify Words Provide a Surprisingly Good Account of Visual Form Priming Effects

arXiv: https://arxiv.org/abs/2302.03992 · HTML: https://mlsanity.com/paper/2302.03992/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 9 of its 52 references that are in the map.
- First posted on arXiv 8 Feb 2023.

## Builds on (most cited first, 9 of 9)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [Densely Connected Convolutional Networks](https://mlsanity.com/paper/1608.06993/) (2016)
- [EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks](https://mlsanity.com/paper/1905.11946/) (2019)
- [ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustness](https://mlsanity.com/paper/1811.12231/) (2018)
- [Are Convolutional Neural Networks or Transformers more like human vision?](https://mlsanity.com/paper/2105.07197/) (2021)
- [Mixed Evidence for Gestalt Grouping in Deep Neural Networks](https://mlsanity.com/paper/2203.07302/) (2022)
- [Learning Online Visual Invariances for Novel Objects via Supervised and Self-Supervised Training](https://mlsanity.com/paper/2110.01476/) (2021)

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

- [Cracking the neural code for word recognition in convolutional neural networks](https://mlsanity.com/paper/2403.06159/) (2024)

## Abstract (arXiv)

A wide variety of orthographic coding schemes and models of visual word identification have been developed to account for masked priming data that provide a measure of orthographic similarity between letter strings. These models tend to include hand-coded orthographic representations with single unit coding for specific forms of knowledge (e.g., units coding for a letter in a given position). Here we assess how well a range of these coding schemes and models account for the pattern of form priming effects taken from the Form Priming Project and compare these findings to results observed with 11 standard deep neural network models (DNNs) developed in computer science. We find that deep convolutional networks (CNNs) perform as well or better than the coding schemes and word recognition models, whereas transformer networks did less well. The success of CNNs is remarkable as their architectures were not developed to support word recognition (they were designed to perform well on object recognition), they classify pixel images of words (rather than artificial encodings of letter strings), and their training was highly simplified (not respecting many key aspects of human experience). In addition to these form priming effects, we find that the DNNs can account for visual similarity effects on priming that are beyond all current psychological models of priming. The findings add to the recent work of (Hannagan et al., 2021) and suggest that CNNs should be given more attention in psychology as models of human visual word recognition.