Search Results for author: H. Sebastian Seung

Found 25 papers, 5 papers with code

Large-scale image segmentation based on distributed clustering algorithms

no code implementations21 Jun 2021 Ran Lu, Aleksandar Zlateski, H. Sebastian Seung

Many approaches to 3D image segmentation are based on hierarchical clustering of supervoxels into image regions.

Chunking Semantic Segmentation

Learning and Segmenting Dense Voxel Embeddings for 3D Neuron Reconstruction

no code implementations21 Sep 2019 Kisuk Lee, Ran Lu, Kyle Luther, H. Sebastian Seung

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.

Electron Microscopy Metric Learning

Siamese Encoding and Alignment by Multiscale Learning with Self-Supervision

no code implementations4 Apr 2019 Eric Mitchell, Stefan Keselj, Sergiy Popovych, Davit Buniatyan, H. Sebastian Seung

We show that siamese encoding enables more accurate alignment than the image pyramids of SPyNet, a previous deep learning approach to coarse-to-fine alignment.

Electron Microscopy Self-Supervised Learning

PZnet: Efficient 3D ConvNet Inference on Manycore CPUs

no code implementations18 Mar 2019 Sergiy Popovych, Davit Buniatyan, Aleksandar Zlateski, Kai Li, H. Sebastian Seung

Convolutional nets have been shown to achieve state-of-the-art accuracy in many biomedical image analysis tasks.

Reconstructing neuronal anatomy from whole-brain images

no code implementations17 Mar 2019 James Gornet, Kannan Umadevi Venkataraju, Arun Narasimhan, Nicholas Turner, Kisuk Lee, H. Sebastian Seung, Pavel Osten, Uygar Sümbül

Reconstructing multiple molecularly defined neurons from individual brains and across multiple brain regions can reveal organizational principles of the nervous system.

Data Augmentation

Convergence of gradient descent-ascent analyzed as a Newtonian dynamical system with dissipation

no code implementations5 Mar 2019 H. Sebastian Seung

A previous convergence theorem due to Kose and Uzawa required the payoff function to be convex in the descent variables, and concave in the ascent variables.

Sample Variance Decay in Randomly Initialized ReLU Networks

no code implementations13 Feb 2019 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.

Learning Metric Graphs for Neuron Segmentation In Electron Microscopy Images

no code implementations31 Jan 2019 Kyle Luther, H. Sebastian Seung

Both empirically and theoretically, it is unclear whether or when deep metric learning is superior to the more conventional approach of directly predicting an affinity graph with a convolutional net.

Electron Microscopy Electron Microscopy Image Segmentation +3

Two "correlation games" for a nonlinear network with Hebbian excitatory neurons and anti-Hebbian inhibitory neurons

no code implementations31 Dec 2018 H. Sebastian Seung

A combination of Legendre and Lagrangian duality yields a zero-sum continuous game between excitatory and inhibitory connections that is solved by the neural network.

Unsupervised learning by a nonlinear network with Hebbian excitatory and anti-Hebbian inhibitory neurons

no code implementations30 Dec 2018 H. Sebastian Seung

The parameters of competition between I-E connections can be adjusted to set the typical decorrelatedness and sparsity of E neuron activity.

Superhuman Accuracy on the SNEMI3D Connectomics Challenge

4 code implementations31 May 2017 Kisuk Lee, Jonathan Zung, Peter Li, Viren Jain, H. Sebastian Seung

For the past decade, convolutional networks have been used for 3D reconstruction of neurons from electron microscopic (EM) brain images.

3D Reconstruction Electron Microscopy Image Segmentation

A correlation game for unsupervised learning yields computational interpretations of Hebbian excitation, anti-Hebbian inhibition, and synapse elimination

no code implementations3 Apr 2017 H. Sebastian Seung, Jonathan Zung

To provide computational interpretations of these aspects of synaptic plasticity, we formulate unsupervised learning as a zero-sum game between Hebbian excitation and anti-Hebbian inhibition in a neural network model.

ZNNi - Maximizing the Inference Throughput of 3D Convolutional Networks on Multi-Core CPUs and GPUs

no code implementations17 Jun 2016 Aleksandar Zlateski, Kisuk Lee, H. Sebastian Seung

Other things being equal, processing a larger image tends to increase throughput, because fractionally less computation is wasted on the borders of the image.

Object Detection Semantic Segmentation

Recursive Training of 2D-3D Convolutional Networks for Neuronal Boundary Prediction

no code implementations NeurIPS 2015 Kisuk Lee, Aleksandar Zlateski, Vishwanathan Ashwin, H. Sebastian Seung

Efforts to automate the reconstruction of neural circuits from 3D electron microscopic (EM) brain images are critical for the field of connectomics.

Boundary Detection Object Recognition

ZNN - A Fast and Scalable Algorithm for Training 3D Convolutional Networks on Multi-Core and Many-Core Shared Memory Machines

2 code implementations22 Oct 2015 Aleksandar Zlateski, Kisuk Lee, H. Sebastian Seung

Applying Brent's theorem to the task dependency graph implies that linear speedup with the number of processors is attainable within the PRAM model of parallel computation, for wide network architectures.

Recursive Training of 2D-3D Convolutional Networks for Neuronal Boundary Detection

2 code implementations NeurIPS 2015 Kisuk Lee, Aleksandar Zlateski, Ashwin Vishwanathan, H. Sebastian Seung

Efforts to automate the reconstruction of neural circuits from 3D electron microscopic (EM) brain images are critical for the field of connectomics.

Boundary Detection

Image Segmentation by Size-Dependent Single Linkage Clustering of a Watershed Basin Graph

no code implementations1 May 2015 Aleksandar Zlateski, H. Sebastian Seung

We present a method for hierarchical image segmentation that defines a disaffinity graph on the image, over-segments it into watershed basins, defines a new graph on the basins, and then merges basins with a modified, size-dependent version of single linkage clustering.

Semantic Segmentation

Algorithms for Non-negative Matrix Factorization

no code implementations NeurIPS 2000 Daniel D. Lee, H. Sebastian Seung

Non-negative matrix factorization (NMF) has previously been shown to be a useful decomposition for multivariate data.

Learning Generative Models with the Up Propagation Algorithm

no code implementations NeurIPS 1997 Jong-Hoon Oh, H. Sebastian Seung

Up-propagation is an algorithm for inverting and learning neural network generative models Sensory input is processed by inverting a model that generates patterns from hidden variables using topdown connections The inversion process is iterative utilizing a negative feedback loop that depends on an error signal propagated by bottomup connections The error signal is also used to learn the generative model from examples The algorithm is benchmarked against principal component analysis in experiments on images of handwritten digits.

Cannot find the paper you are looking for? You can Submit a new open access paper.