224 citations · 592 across the 25 of their papers we have counts for
27 papers
DDGM: Solving inverse problems by Diffusive Denoising of Gradient-based Minimization
Kyle Luther, H. Sebastian Seung
Inverse problems generally require a regularizer or prior for a good solution. A recent trend is to train a convolutional net to denoise images, and use this net as a prior when so…
Stretched sinograms for limited-angle tomographic reconstruction with neural networks
Kyle Luther, Sebastian Seung
We present a direct method for limited angle tomographic reconstruction using convolutional networks. The key to our method is to first stretch every tilt view in the direction per…
Stacked unsupervised learning with a network architecture found by supervised meta-learning
Kyle Luther, H. Sebastian Seung
Stacked unsupervised learning (SUL) seems more biologically plausible than backpropagation, because learning is local to each layer. But SUL has fallen far short of backpropagation…
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…
Large-scale image segmentation based on distributed clustering algorithms
Ran Lu, Aleksandar Zlateski, H. Sebastian Seung
Many approaches to 3D image segmentation are based on hierarchical clustering of supervoxels into image regions. Here we describe a distributed algorithm capable of handling a trem…
Learning and Segmenting Dense Voxel Embeddings for 3D Neuron Reconstruction
Kisuk Lee, Ran Lu, Kyle Luther +1
We show dense voxel embeddings learned via deep metric learning can be employed to produce a highly accurate segmentation of neurons from 3D electron microscopy images. A "metric g…
Chunkflow: Distributed Hybrid Cloud Processing of Large 3D Images by Convolutional Nets
Jingpeng Wu, William M. Silversmith, Kisuk Lee +1
It is now common to process volumetric biomedical images using 3D Convolutional Networks (ConvNets). This can be challenging for the teravoxel and even petavoxel images that are be…
Convolutional nets for reconstructing neural circuits from brain images acquired by serial section electron microscopy
Kisuk Lee, Nicholas Turner, Thomas Macrina +3
Neural circuits can be reconstructed from brain images acquired by serial section electron microscopy. Image analysis has been performed by manual labor for half a century, and eff…
Siamese Encoding and Alignment by Multiscale Learning with Self-Supervision
Eric Mitchell, Stefan Keselj, Sergiy Popovych +2
We propose a method of aligning a source image to a target image, where the transform is specified by a dense vector field. The two images are encoded as feature hierarchies by sia…
Synaptic Partner Assignment Using Attentional Voxel Association Networks
Nicholas Turner, Kisuk Lee, Ran Lu +3
Connectomics aims to recover a complete set of synaptic connections within a dataset imaged by volume electron microscopy. Many systems have been proposed for locating synapses, an…
PZnet: Efficient 3D ConvNet Inference on Manycore CPUs
Sergiy Popovych, Davit Buniatyan, Aleksandar Zlateski +2
Convolutional nets have been shown to achieve state-of-the-art accuracy in many biomedical image analysis tasks. Many tasks within biomedical analysis domain involve analyzing volu…
Reconstructing neuronal anatomy from whole-brain images
James Gornet, Kannan Umadevi Venkataraju, Arun Narasimhan +5
Reconstructing multiple molecularly defined neurons from individual brains and across multiple brain regions can reveal organizational principles of the nervous system. However, hi…
Convergence of gradient descent-ascent analyzed as a Newtonian dynamical system with dissipation
H. Sebastian Seung
A dynamical system is defined in terms of the gradient of a payoff function. Dynamical variables are of two types, ascent and descent. The ascent variables move in the direction of…
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…
Two "correlation games" for a nonlinear network with Hebbian excitatory neurons and anti-Hebbian inhibitory neurons
H. Sebastian Seung
A companion paper introduces a nonlinear network with Hebbian excitatory (E) neurons that are reciprocally coupled with anti-Hebbian inhibitory (I) neurons and also receive Hebbian…
Unsupervised learning by a nonlinear network with Hebbian excitatory and anti-Hebbian inhibitory neurons
H. Sebastian Seung
This paper introduces a rate-based nonlinear neural network in which excitatory (E) neurons receive feedforward excitation from sensory (S) neurons, and inhibit each other through…
An Error Detection and Correction Framework for Connectomics
Jonathan Zung, Ignacio Tartavull, Kisuk Lee +1
We define and study error detection and correction tasks that are useful for 3D reconstruction of neurons from electron microscopic imagery, and for image segmentation more general…
Superhuman Accuracy on the SNEMI3D Connectomics Challenge
Kisuk Lee, Jonathan Zung, Peter Li +2
For the past decade, convolutional networks have been used for 3D reconstruction of neurons from electron microscopic (EM) brain images. Recent years have seen great improvements i…
Deep Learning Improves Template Matching by Normalized Cross Correlation
Davit Buniatyan, Thomas Macrina, Dodam Ih +2
Template matching by normalized cross correlation (NCC) is widely used for finding image correspondences. We improve the robustness of this algorithm by preprocessing images with "…
A correlation game for unsupervised learning yields computational interpretations of Hebbian excitation, anti-Hebbian inhibition, and synapse elimination
H. Sebastian Seung, Jonathan Zung
Much has been learned about plasticity of biological synapses from empirical studies. Hebbian plasticity is driven by correlated activity of presynaptic and postsynaptic neurons. S…
ZNNi - Maximizing the Inference Throughput of 3D Convolutional Networks on Multi-Core CPUs and GPUs
Aleksandar Zlateski, Kisuk Lee, H. Sebastian Seung
Sliding window convolutional networks (ConvNets) have become a popular approach to computer vision problems such as image segmentation, and object detection and localization. Here…
Automatic Neuron Detection in Calcium Imaging Data Using Convolutional Networks
Noah J. Apthorpe, Alexander J. Riordan, Rob E. Aguilar +4
Calcium imaging is an important technique for monitoring the activity of thousands of neurons simultaneously. As calcium imaging datasets grow in size, automated detection of indiv…
ZNN - A Fast and Scalable Algorithm for Training 3D Convolutional Networks on Multi-Core and Many-Core Shared Memory Machines
Aleksandar Zlateski, Kisuk Lee, H. Sebastian Seung
Convolutional networks (ConvNets) have become a popular approach to computer vision. It is important to accelerate ConvNet training, which is computationally costly. We propose a n…