Fabian Tschopp
YOU?
Author Swipe
View article: Connectome-constrained networks predict neural activity across the fly visual system
Connectome-constrained networks predict neural activity across the fly visual system Open
We can now measure the connectivity of every neuron in a neural circuit 1–9 , but we cannot measure other biological details, including the dynamical characteristics of each neuron. The degree to which measurements of connectivity alone ca…
View article: Connectome-constrained deep mechanistic networks predict neural responses across the fly visual system at single-neuron resolution
Connectome-constrained deep mechanistic networks predict neural responses across the fly visual system at single-neuron resolution Open
We can now measure the connectivity of every neuron in a neural circuit, but we are still blind to other biological details, including the dynamical characteristics of each neuron. The degree to which connectivity measurements alone can in…
View article: Tuning of Mixture-of-Experts Mixed-Precision Neural Networks
Tuning of Mixture-of-Experts Mixed-Precision Neural Networks Open
Deep learning has become a useful data analysis method, however mainstream adaption in distributed computer software and embedded devices has been low so far. Often, adding deep learning inference in mainstream applications and devices req…
View article: A Connectome Based Hexagonal Lattice Convolutional Network Model of the Drosophila Visual System
A Connectome Based Hexagonal Lattice Convolutional Network Model of the Drosophila Visual System Open
What can we learn from a connectome? We constructed a simplified model of the first two stages of the fly visual system, the lamina and medulla. The resulting hexagonal lattice convolutional network was trained using backpropagation throug…
View article: A Connectome Based Hexagonal Lattice Convolutional Network Model of the\n Drosophila Visual System
A Connectome Based Hexagonal Lattice Convolutional Network Model of the\n Drosophila Visual System Open
What can we learn from a connectome? We constructed a simplified model of the\nfirst two stages of the fly visual system, the lamina and medulla. The\nresulting hexagonal lattice convolutional network was trained using\nbackpropagation thr…
View article: Large Scale Image Segmentation with Structured Loss Based Deep Learning for Connectome Reconstruction
Large Scale Image Segmentation with Structured Loss Based Deep Learning for Connectome Reconstruction Open
We present a method combining affinity prediction with region agglomeration, which improves significantly upon the state of the art of neuron segmentation from electron microscopy (EM) in accuracy and scalability. Our method consists of a …
View article: A Deep Structured Learning Approach Towards Automating Connectome Reconstruction from 3D Electron Micrographs.
A Deep Structured Learning Approach Towards Automating Connectome Reconstruction from 3D Electron Micrographs. Open
View article: Anisotropic EM Segmentation by 3D Affinity Learning and Agglomeration
Anisotropic EM Segmentation by 3D Affinity Learning and Agglomeration Open
The field of connectomics has recently produced neuron wiring diagrams from relatively large brain regions from multiple animals. Most of these neural reconstructions were computed from isotropic (e.g., FIBSEM) or near isotropic (e.g., SBE…
View article: Efficient convolutional neural networks for pixelwise classification on heterogeneous hardware systems
Efficient convolutional neural networks for pixelwise classification on heterogeneous hardware systems Open
This work presents and analyzes three convolutional neural network (CNN) models for efficient pixelwise classification of images. When using convolutional neural networks to classify single pixels in patches of a whole image, a lot of redu…
View article: Robust Large-Scale Localization in 3D Point Clouds Revisited
Robust Large-Scale Localization in 3D Point Clouds Revisited Open
We tackle the problem of getting a full 6-DOF pose estimation of a query image inside a given point cloud. This technical report re-evaluates the algorithms proposed by Y. Li et al. "Worldwide Pose Estimation using 3D Point Cloud". Our cod…