Search Results for author:
Found 6 papers, 3 papers with code
Understanding the computational demands underlying visual reasoning
Our analysis reveals a novel taxonomy of visual reasoning tasks, which can be primarily explained by both the type of relations (same-different vs. spatial-relation judgments) and the number of relations used to compose the underlying rules.
On the role of feedback in visual processing: a predictive coding perspective
That is, we let the optimization process determine whether top-down connections and predictive coding dynamics are functionally beneficial.
Predify: Augmenting deep neural networks with brain-inspired predictive coding dynamics
The reconstruction errors are used to iteratively update the network's representations across timesteps, and to optimize the network's feedback weights over the natural image dataset-a form of unsupervised training.
GAttANet: Global attention agreement for convolutional neural networks
We demonstrate the usefulness of this brain-inspired Global Attention Agreement network (GAttANet) for various convolutional backbones (from a simple 5-layer toy model to a standard ResNet50 architecture) and datasets (CIFAR10, CIFAR100, Imagenet-1k).
Brain-inspired predictive coding dynamics improve the robustness of deep neural networks
The reconstruction errors are used to iteratively update the network’s representations across timesteps, and to optimize the network's feedback weights over the natural image dataset--a form of unsupervised training.
Which Neural Network Architecture matches Human Behavior in Artificial Grammar Learning?
Our results show that both architectures can 'learn' (via error back-propagation) the grammars after the same number of training sequences as humans do, but recurrent networks perform closer to humans than feedforward ones, irrespective of the grammar complexity level.
Neurons and Cognition Human-Computer Interaction
