Search Results for author:
Found 7 papers, 5 papers with code
Putting An End to End-to-End: Gradient-Isolated Learning of Representations
We propose a novel deep learning method for local self-supervised representation learning that does not require labels nor end-to-end backpropagation but exploits the natural order in data instead.
Ranked #60 on
Image Classification
on STL-10
Representation Learning
Self-Supervised Audio Classification
+2
Initialized Equilibrium Propagation for Backprop-Free Training
In response to this, Scellier & Bengio (2017) proposed Equilibrium Propagation - a method for gradient-based train- ing of neural networks which uses only local learning rules and, crucially, does not rely on neurons having a mechanism for back-propagating an error gradient.
Learning a Representation Map for Robot Navigation using Deep Variational Autoencoder
For the navigation problem, we map the starting image and destination image to the latent space, then optimize a path on the learned manifold connecting the two points, and finally map the path back through decoder to a sequence of images.
Explaining the Mistakes of Neural Networks with Latent Sympathetic Examples
Neural networks make mistakes.
Temporally Efficient Deep Learning with Spikes
We present a variant on backpropagation for neural networks in which computation scales with the rate of change of the data - not the rate at which we process the data.
Sigma Delta Quantized Networks
Thus the amount of computation that the network does scales with the amount of change in the input and layer activations, rather than the size of the network.
Deep Spiking Networks
Our network is "spiking" in the sense that our neurons accumulate their activation into a potential over time, and only send out a signal (a "spike") when this potential crosses a threshold and the neuron is reset.
