Search Results for author:
Found 3 papers, 0 papers with code
Learning where to learn
Finding neural network weights that generalize well from small datasets is difficult.
Ghost Units Yield Biologically Plausible Backprop in Deep Neural Networks
This reduced system combines the essential elements to have a working biologically abstracted analogue of backpropagation with a simple formulation and proofs of the associated results.
Feedforward Initialization for Fast Inference of Deep Generative Networks is biologically plausible
We find conditions under which a simple feedforward computation is a very good initialization for inference, after the input units are clamped to observed values.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
