Back to Search
Start Over
Neural Coding Strategies for Event-Based Vision Data
- Source :
- ICASSP
- Publication Year :
- 2020
- Publisher :
- IEEE, 2020.
-
Abstract
- Neural coding schemes are powerful tools used within neuroscience. This paper introduces three different neural coding scheme formations for event-based vision data which are designed to emulate the neural behaviour exhibited by neurons under stimuli. Presented are phase-of-firing and two sparse neural coding schemes. It is determined that machine learning approaches, i.e. Convolutional Neural Network combined with a Stacked Autoencoder network, produce powerful descriptors of the patterns within events. These coding schemes are deployed in an existing action recognition template and evaluated using two popular event-based data sets.
- Subjects :
- Quantitative Biology::Neurons and Cognition
business.industry
Computer science
Event based
Computer Science::Neural and Evolutionary Computation
Feature extraction
Cognitive neuroscience of visual object recognition
Pattern recognition
02 engineering and technology
Autoencoder
Convolutional neural network
03 medical and health sciences
0302 clinical medicine
0202 electrical engineering, electronic engineering, information engineering
020201 artificial intelligence & image processing
Artificial intelligence
Neural coding
business
030217 neurology & neurosurgery
Subjects
Details
- Database :
- OpenAIRE
- Journal :
- ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
- Accession number :
- edsair.doi...........04929c0ac53c643e67ae55ce6c27b1a2