Presenter: Jakob
Theory journal club, 07.01.2022
NeurIPS 2020
system1: 75%
system2: 75%
system1: 100%
system2: 50%
system1: 50%
system2: 100%
Consider two systems i and j:
How much do their decisions overlap?
observed overlap:
number of equal responses
error consistency
remove expected overlap
for high expected overlap additional overlap is more relevant
accuracy
expected overlap:
(binomial)
consistency by chance
"We developed CORnet-S, a shallow ANN with four anatomically mapped areas and recurrent connectivity, guided by Brain-Score, a new large-scale composite of neural and behavioral benchmarks for quantifying the functional fidelity of models of the primate ventral visual stream. Despite being significantly shallower than most models, CORnet-S is the top model on Brain-Score and outperforms similarly compact models on ImageNet. Moreover, our extensive analyses of CORnet-S circuitry variants reveal that recurrence is the main predictive factor of both Brain-Score and ImageNet top-1 performance. Finally, we report that the temporal evolution of the CORnet-S "IT" neural population resembles the actual monkey IT population dynamics. Taken together, these results establish CORnet-S, a compact, recurrent ANN, as the current best model of the primate ventral visual stream."
Kubelius ... DiCarlo: Brain-Like Object Recognition with High-Performing Shallow Recurrent ANNs [NeurIPS 2019 (oral)]