Deep Supervised, but Not Unsupervised, Models May Explain IT Cortical Representation

@article{KhalighRazavi2014DeepSB,
  title={Deep Supervised, but Not Unsupervised, Models May Explain IT Cortical Representation},
  author={Seyed-Mahdi Khaligh-Razavi and N. Kriegeskorte},
  journal={PLoS Computational Biology},
  year={2014},
  volume={10}
}
  • Seyed-Mahdi Khaligh-Razavi, N. Kriegeskorte
  • Published 2014
  • Computer Science, Medicine
  • PLoS Computational Biology
  • Inferior temporal (IT) cortex in human and nonhuman primates serves visual object recognition. Computational object-vision models, although continually improving, do not yet reach human performance. It is unclear to what extent the internal representations of computational models can explain the IT representation. Here we investigate a wide range of computational model representations (37 in total), testing their categorization performance and their ability to account for the IT… CONTINUE READING
    688 Citations
    A performance-optimized model of neural responses across the ventral visual stream
    • 17
    • Highly Influenced
    • PDF
    Invariant visual object recognition: biologically plausible approaches
    • 27
    • PDF
    CORnet: Modeling the Neural Mechanisms of Core Object Recognition
    • 54
    • PDF
    Deep Neural Networks as a Computational Model for Human Shape Sensitivity
    • 142
    • Highly Influenced
    • PDF
    Deep Learning Predicts Correlation between a Functional Signature of Higher Visual Areas and Sparse Firing of Neurons
    • 6
    • PDF
    An empirical model of activity in macaque inferior temporal cortex
    • 1
    • Highly Influenced
    BETTER CHARACTERIZING MOUSE VISUAL CORTEX

    References

    SHOWING 1-10 OF 106 REFERENCES
    Deep Neural Networks Rival the Representation of Primate IT Cortex for Core Visual Object Recognition
    • 498
    • PDF
    Performance-optimized hierarchical models predict neural responses in higher visual cortex
    • 939
    • PDF
    Representational dynamics of object vision: the first 1000 ms.
    • 277
    • PDF