AI Chat AI Image Generator AI Video Text to Speech

Sparse 3D convolutional neural networks

05/12/2015

∙

by Ben Graham, et al.

∙

∙

We have implemented a convolutional neural network designed for processing sparse three-dimensional input data. The world we live in is three dimensional so there are a large number of potential applications including 3D object recognition and analysis of space-time objects. In the quest for efficiency, we experiment with CNNs on the 2D triangular-lattice and 3D tetrahedral-lattice.

page 2

page 9

research

∙ 12/23/2020

Lattice gauge equivariant convolutional neural networks

We propose Lattice gauge equivariant Convolutional Neural Networks (L-CN...

0 Matteo Favoni, et al. ∙

research

∙ 11/26/2018

Unsupervised learning with sparse space-and-time autoencoders

We use spatially-sparse two, three and four dimensional convolutional au...

0 Benjamin Graham, et al. ∙

research

∙ 12/20/2014

Permutohedral Lattice CNNs

This paper presents a convolutional layer that is able to process sparse...

0 Martin Kiefel, et al. ∙

research

∙ 03/20/2023

Geometrical aspects of lattice gauge equivariant convolutional neural networks

Lattice gauge equivariant convolutional neural networks (L-CNNs) are a f...

0 Jimmy Aronsson, et al. ∙

research

∙ 12/01/2022

Applications of Lattice Gauge Equivariant Neural Networks

The introduction of relevant physical information into neural network ar...

0 Matteo Favoni, et al. ∙

research

∙ 11/26/2018

A Convolutional Neural Network based Live Object Recognition System as Blind Aid

This paper introduces a live object recognition system that serves as a ...

0 Kedar Potdar, et al. ∙

research

∙ 02/22/2018

SPLATNet: Sparse Lattice Networks for Point Cloud Processing

We present a network architecture for processing point clouds that direc...

0 Hang Su, et al. ∙