TactileSGNet: A Spiking Graph Neural Network for Event-based Tactile Object Recognition.
Fuqiang GuWeicong SngTasbolat TaunyazovHarold SohPublished in: IROS (2020)
Keyphrases
- neural network
- object recognition
- feed forward
- neuron model
- graph matching
- artificial neural networks
- computer vision
- graph model
- back propagation
- graph theory
- pattern recognition
- single neuron
- random walk
- event driven
- graph structure
- learning rules
- graph representation
- directed graph
- d objects
- recurrent neural networks
- spiking neurons
- fuzzy logic
- image features
- bio inspired
- hebbian learning
- directed acyclic graph
- hidden layer
- spiking neural networks
- neural network is trained
- bipartite graph
- neural nets
- connected components
- weighted graph
- self organizing maps
- genetic algorithm
- knn
- semi supervised
- natural images
- image representation
- structured data
- fault diagnosis
- graph theoretic
- multilayer perceptron
- object categories
- training process
- multi layer