5 papers
Kernel similarity matching with Hebbian neural networks
Kyle Luther, H. Sebastian Seung
Recent works have derived neural networks with online correlation-based learning rules to perform \textit{kernel similarity matching}. These works applied existing linear similarit…
Sensitivity of sparse codes to image distortions
Kyle Luther, H. Sebastian Seung
Sparse coding has been proposed as a theory of visual cortex and as an unsupervised algorithm for learning representations. We show empirically with the MNIST dataset that sparse c…
The HST See Change Program: I. Survey Design, Pipeline, and Supernova Discoveries
Brian Hayden, David Rubin, Kyle Boone +53
The See Change survey was designed to make cosmological measurements by efficiently discovering high-redshift Type Ia supernovae (SNe Ia) and improving cluster mass measureme…
Sample Variance Decay in Randomly Initialized ReLU Networks
Kyle Luther, H. Sebastian Seung
Before training a neural net, a classic rule of thumb is to randomly initialize the weights so the variance of activations is preserved across layers. This is traditionally interpr…
Learning Metric Graphs for Neuron Segmentation In Electron Microscopy Images
Kyle Luther, H. Sebastian Seung
In the deep metric learning approach to image segmentation, a convolutional net densely generates feature vectors at the pixels of an image. Pairs of feature vectors are trained to…