/explore
|
You are here 
|
polukhin.tech | ||
| | | | |
tomhume.org
|
|
| | | | | I don't remember how I came across it, but this is one of the most exciting papers I've read recently. The authors train a neural network that tries to identify the next in a sequence of MNIST samples, presented in digit order. The interesting part is that when they include a proxy for energy usage in the loss function (i.e. train it to be more energy-efficient), the resulting network seems to exhibit the characteristics of predictive coding: some units seem to be responsible for predictions, others for encoding prediction error. | |
| | | | |
d2l.ai
|
|
| | | | | ||
| | | | |
coen.needell.org
|
|
| | | | | In my last post on computer vision and memorability, I looked at an already existing model and started experimenting with variations on that architecture. The most successful attempts were those that use Residual Neural Networks. These are a type of deep neural network built to mimic specific visual structures in the brain. ResMem, one of the new models, uses a variation on ResNet in its architecture to leverage that optical identification power towards memorability estimation. | |
| | | | |
www.hamza.se
|
|
| | | A walkthrough of implementing a neural network from scratch in Python, exploring what makes these seemingly complex systems actually quite straightforward. | ||
