Brain-Score: Which Artificial Neural Network for Object Recognition is most Brain-Like?

The internal representations of early deep artificial neural networks (ANNs) were found to be remarkably similar to the internal neural representations measured experimentally in the primate brain. Here we ask, as deep ANNs have continued to evolve, are they becoming more or less brain-like? ANNs that are most functionally similar to the brain will contain mechanisms that are most like those used by the brain. We therefore developed Brain-Score – a composite of multiple neural and behavioral benchmarks that score any ANN on how similar it is to the brain’s mechanisms for core object recognition – and we deployed it to evaluate a wide range of state-of-the-art deep ANNs. Using this scoring system, we here report that: (1) DenseNet-169, CORnet-S and ResNet-101 are the most brain-like ANNs. (2) There remains considerable variability in neural and behavioral responses that is not predicted by any ANN, suggesting that no ANN model has yet captured all the relevant mechanisms. (3) Extending prior work, we found that gains in ANN ImageNet performance led to gains on Brain-Score. However, correlation weakened at ≥ 70% top-1 ImageNet performance, suggesting that additional guidance from neuroscience is needed to make further advances in capturing brain mechanisms. (4) We uncovered smaller (i.e. less complex) ANNs that are more brain-like than many of the best-performing ImageNet models, which suggests the opportunity to simplify ANNs to better understand the ventral stream. The scoring system used here is far from complete. However, we propose that evaluating and tracking model-benchmark correspondences through a Brain-Score that is regularly updated with new brain data is an exciting opportunity: experimental benchmarks can be used to guide machine network evolution, and machine networks are mechanistic hypotheses of the brain’s network and thus drive next experiments. To facilitate both of these, we release [Brain-Score.org][1]: a platform that hosts the neural and behavioral benchmarks, where ANNs for visual processing can be submitted to receive a Brain-Score and their rank relative to other models, and where new experimental data can be naturally incorporated. [1]: http://Brain-Score.org

Brain-Score: Which Artificial Neural Network for Object Recognition is most Brain-Like? | bioRxiv Skip to main content New Results Brain-Score: Which Artificial Neural Network for Object Recognition is most Brain-Like? View ORCID Profile Martin Schrimpf , View ORCID Profile Jonas Kubilius , Ha Hong , Najib J. Majaj , Rishi Rajalingham , Elias B. Issa , View ORCID Profile Kohitij Kar , View ORCID Profile Pouya Bashivan , Jonathan Prescott-Roy , Franziska Geiger , Kailyn Schmidt , Daniel L. K. Yamins , View ORCID Profile James J. DiCarlo doi: https://doi.org/10.1101/407007 Martin Schrimpf 1 Depa

related reading

• Zoom In: An Introduction to Circuitsdistill.pub
• A deep learning framework for neuroscience - PMCncbi.nlm.nih.gov
• A critique of pure learning and what artificial neural networks can learn from animal brains | Nature Communicationsnature.com
• Distill — Latest articles about machine learningdistill.pub
• Neural networks and deep learningneuralnetworksanddeeplearning.com
• Multimodal Neurons in Artificial Neural Networksdistill.pub
• Analogies between Biology and Deep Learning [rough note] -- colah's blogcolah.github.io
• How Computationally Complex Is a Single Neuron? | Quanta Magazinequantamagazine.org
• Building machines that learn and think like people | Behavioral and Brain Sciences | Cambridge Corecambridge.org
• Human-like Neural Nets by Catapulting · Gwern.netgwern.net
• So how does learning work?cs.mcgill.ca
• The Decade of Deep Learning | Leo Gaobmk.sh