Brain-Like Object Recognition with High-Performing Shallow Recurrent ANNs

09/13/2019
by   Jonas Kubilius, et al.
0

Deep convolutional artificial neural networks (ANNs) are the leading class of candidate models of the mechanisms of visual processing in the primate ventral stream. While initially inspired by brain anatomy, over the past years, these ANNs have evolved from a simple eight-layer architecture in AlexNet to extremely deep and branching architectures, demonstrating increasingly better object categorization performance, yet bringing into question how brain-like they still are. In particular, typical deep models from the machine learning community are often hard to map onto the brain's anatomy due to their vast number of layers and missing biologically-important connections, such as recurrence. Here we demonstrate that better anatomical alignment to the brain and high performance on machine learning as well as neuroscience measures do not have to be in contradiction. 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.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
05/25/2019

Training neural networks to have brain-like representations improves object recognition performance

The current state-of-the-art object recognition algorithms, deep convolu...
research
07/20/2019

Recurrent Connections Aid Occluded Object Recognition by Discounting Occluders

Recurrent connections in the visual cortex are thought to aid object rec...
research
03/22/2022

Improving Neural Predictivity in the Visual Cortex with Gated Recurrent Connections

Computational models of vision have traditionally been developed in a bo...
research
03/14/2019

Recurrence required to capture the dynamic computations of the human ventral visual stream

The visual system is an intricate network of brain regions that enables ...
research
07/14/2021

Passive attention in artificial neural networks predicts human visual selectivity

Developments in machine learning interpretability techniques over the pa...
research
06/20/2018

Task-Driven Convolutional Recurrent Models of the Visual System

Feed-forward convolutional neural networks (CNNs) are currently state-of...
research
08/22/2022

Different Spectral Representations in Optimized Artificial Neural Networks and Brains

Recent studies suggest that artificial neural networks (ANNs) that match...

Please sign up or login with your details

Forgot password? Click here to reset