CoChat

Number detectors spontaneously emerge in a deep neural network designed for visual object recognition

Open access
Nasr, Khaled, Viswanathan, Pooja, Nieder, Andreas · 2019 · Science Advances

The DOI matches its Crossref record; 45 of the 45 references it cites were found in a registry or an index.

Abstract

A deep neural network trained only on visual object recognition develops tuned number detectors reminiscent of real neurons.

Overview

The claims and statistics of this paper haven’t been checked yet.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1126/sciadv.aav7903

Cites

45 of 45 references verified0 citation errors · 0 not checkable

Statistics

Figures

Fig. 1 An HCNN for object recognition. (A) Simplified architecture of the HCNN. The feature extraction network consists of convolutional layers that compute multiple feature maps. Each feature map represents the presence of a certain visual feature at all possible locations in the input and is computed by convolving the input with a filter and then applying a nonlinear activation function. Max-pooling layers aggregate responses by computing the maximum response in small nonoverlapping regions of their input. The classification network consists of a global average-pooling layer that computes the average response in each input feature map, and a fully connected layer where the response of each unit represents the probability that a specific object class is present in the input image. (B) Successful classification of a wolf spider by the network from other arthropods is shown as an example. Example images representative of those used in the test set and the top 5 predictions made by the network for each image ranked by confidence. Ground-truth labels are shown above each image. Images shown here are from the public domain (Wikimedia Commons).
Fig. 1 An HCNN for object recognition. (A) Simplified architecture of the HCNN. The feature extraction network consists of convolutional layers that compute multiple feature maps. Each feature map represents the presence of a certain visual feature at all possible locations in the input and is computed by convolving the input with a filter and then applying a nonlinear activation function. Max-pooling layers aggregate responses by computing the maximum response in small nonoverlapping regions of their input. The classification network consists of a global average-pooling layer that computes the average response in each input feature map, and a fully connected layer where the response of each unit represents the probability that a specific object class is present in the input image. (B) Successful classification of a wolf spider by the network from other arthropods is shown as an example. Example images representative of those used in the test set and the top 5 predictions made by the network for each image ranked by confidence. Ground-truth labels are shown above each image. Images shown here are from the public domain (Wikimedia Commons).CC BY-NC · PubMed Central
Fig. 2 Numerosity-tuned units emerging in the HCNN. (A) Examples of the stimuli used to assess numerosity encoding. Standard stimuli contain dots of the same average radius. Dots in Area & Density stimuli have a constant total area and density across all numerosities. Dots in Shape & Convex hull stimuli have random shapes and a uniform pentagon convex hull (for numerosities >4). (B) Tuning curves for individual numerosity-selective network units. Colored curves show the average responses for each stimulus set. Black curves show the average responses over all stimulus set. Error bars indicate SE measure. PN, preferred numerosity. (C) Same as (B), but for neurons in monkey prefrontal cortex (20). Only the average responses over all stimulus sets are shown. (D) Distribution of preferred numerosities of the numerosity-selective network units. (E) Same as (D), but for real neurons recorded in monkey prefrontal cortex [data from (20)].
Fig. 2 Numerosity-tuned units emerging in the HCNN. (A) Examples of the stimuli used to assess numerosity encoding. Standard stimuli contain dots of the same average radius. Dots in Area & Density stimuli have a constant total area and density across all numerosities. Dots in Shape & Convex hull stimuli have random shapes and a uniform pentagon convex hull (for numerosities >4). (B) Tuning curves for individual numerosity-selective network units. Colored curves show the average responses for each stimulus set. Black curves show the average responses over all stimulus set. Error bars indicate SE measure. PN, preferred numerosity. (C) Same as (B), but for neurons in monkey prefrontal cortex (20). Only the average responses over all stimulus sets are shown. (D) Distribution of preferred numerosities of the numerosity-selective network units. (E) Same as (D), but for real neurons recorded in monkey prefrontal cortex [data from (20)].CC BY-NC · PubMed Central
Fig. 3 Tuning curves of numerosity-selective network units. Average tuning curves of numerosity-selective network units tuned to each numerosity. Each curve is computed by averaging the responses of all numerosity-selective units that have the same preferred numerosity. The pooled responses are normalized to the 0 to 1 range. Preferred numerosity and number of numerosity-selective network units are indicated above each curve. Error bars indicate SE measure.
Fig. 3 Tuning curves of numerosity-selective network units. Average tuning curves of numerosity-selective network units tuned to each numerosity. Each curve is computed by averaging the responses of all numerosity-selective units that have the same preferred numerosity. The pooled responses are normalized to the 0 to 1 range. Preferred numerosity and number of numerosity-selective network units are indicated above each curve. Error bars indicate SE measure.CC BY-NC · PubMed Central
Fig. 4 Tuning properties of numerosity-selective network units. (A) Left: Average tuning curves for network units preferring each numerosity plotted on a linear scale. Right: Same tuning curves plotted on a logarithmic scale. (B) Average goodness-of-fit measure for fitting Gaussian functions to the tuning curves on different scales [Plinear-log = 0.009; Plinear-pow(1/2) = 0.003; Plinear-pow(1/3) = 0.001]. (C) SD of the best-fitting Gaussian function for each of the tuning curves of numerosity-selective network units for different scales.
Fig. 4 Tuning properties of numerosity-selective network units. (A) Left: Average tuning curves for network units preferring each numerosity plotted on a linear scale. Right: Same tuning curves plotted on a logarithmic scale. (B) Average goodness-of-fit measure for fitting Gaussian functions to the tuning curves on different scales [Plinear-log = 0.009; Plinear-pow(1/2) = 0.003; Plinear-pow(1/3) = 0.001]. (C) SD of the best-fitting Gaussian function for each of the tuning curves of numerosity-selective network units for different scales.CC BY-NC · PubMed Central
Fig. 5 Relevance of numerosity-selective units to network performance. Average activity of numerosity-selective network units shown as a function of numerical distance between preferred numerosities and sample numerosities in the matching task. Left: Data from network units. Responses were average separately for correct trials (black) and error trials (gray). Responses during error trials are normalized to the maximum average response during correct trials (P = 0.019). Right: Same plot but for real neurons recorded from monkey prefrontal cortex [data from (20)].
Fig. 5 Relevance of numerosity-selective units to network performance. Average activity of numerosity-selective network units shown as a function of numerical distance between preferred numerosities and sample numerosities in the matching task. Left: Data from network units. Responses were average separately for correct trials (black) and error trials (gray). Responses during error trials are normalized to the maximum average response during correct trials (P = 0.019). Right: Same plot but for real neurons recorded from monkey prefrontal cortex [data from (20)].CC BY-NC · PubMed Central
Fig. 6 Performance of the HCNN model in the numerosity matching task. (A) Left: Performance functions resulting from the discrimination of numerosities plotted on a linear scale. Each curve shows the probability of the model predicting that the sample image contains the same number of items as the test image (peak of the function). Sample numerosity is indicated above each curve. Right: Same performance functions but plotted on a logarithmic scale. (B) Average goodness-of-fit measure for fitting Gaussian functions to the performance tuning curves on different scales [Plinear-log = 0.003; Plinear-pow(1/2) = 0.049; Plinear-pow(1/3) = 0.016]. *P < 0.05. (C) SD of the best-fitting Gaussian function for each of the performance tuning curves for different scales.
Fig. 6 Performance of the HCNN model in the numerosity matching task. (A) Left: Performance functions resulting from the discrimination of numerosities plotted on a linear scale. Each curve shows the probability of the model predicting that the sample image contains the same number of items as the test image (peak of the function). Sample numerosity is indicated above each curve. Right: Same performance functions but plotted on a logarithmic scale. (B) Average goodness-of-fit measure for fitting Gaussian functions to the performance tuning curves on different scales [Plinear-log = 0.003; Plinear-pow(1/2) = 0.049; Plinear-pow(1/3) = 0.016]. *P < 0.05. (C) SD of the best-fitting Gaussian function for each of the performance tuning curves for different scales.CC BY-NC · PubMed Central

Verification

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

A few free checks a day · papers already verified open instantly · results are public

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Citations

Cites

Show all 45 references

Research works printed but not linked: 3

  1. S. Dehaene The Number Sense (Oxford Univ. Press 1999).
  2. Y. LeCun Y. Bengio Convolutional networks for images speech and time-series in The Handbook of Brain Theory and Neural Networks (MIT Press 1995) vol. 3361 pp. 255–258.
  3. S. Carey The Origin of Concepts: Oxford Series in Cognitive Development (Oxford Univ. Press 2009).

Cited by

See all 116

Metadata

Authors
Nasr, K., Viswanathan, P., & Nieder, A.
Affiliations
University of Tübingen (DE)
Corresponding author
Nieder, Andreas
Venue
Science Advances
Published
2019-05-03
Volume
5
Issue
5
Pages
eaav7903-eaav7903
ISSN
2375-2548 (ISSN-L)
OpenAlex
W2944629072
Cited by
110
References
41
Citations by year
2026: 4 · 2025: 11 · 2024: 18 · 2023: 19 · 2022: 19 · 2021: 20 · 2020: 15 · 2019: 4
FWCI
11.34
Type
journal article
Language
en
Open access
Licence
cc-by-nc
Locations
  • Science Advances (publishedVersion, cc-by-nc)
  • PubMed Central (publishedVersion, cc-by-nc)
  • PubMed (publishedVersion)
Funders
Deutsche Forschungsgemeinschaft (NI 618/10-1)
Topics
  • Social Sciences › Psychology › Developmental and Educational Psychology › Cognitive and developmental aspects of mathematical skills
  • Life Sciences › Neuroscience › Cognitive Neuroscience › Visual perception and processing mechanisms
  • Social Sciences › Psychology › Experimental and Cognitive Psychology › Multisensory perception and integration
Keywords
number sense, numerosity, spontaneous emergence, deep neural network, visual object recognition, number discrimination, Weber-Fechner law, biologically inspired models, visual system
MeSH terms
Animals, Humans, Models, Biological, Neurons, Visual Perception, Neural Networks, Computer

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review

Data sources

Bibliographic data: Semantic Scholar, OpenAlex, Crossref.

Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).

Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.