Biologically Inspired Oscillating Activation Functions Can Bridge the Performance Gap between Biological and Artificial Neurons.
Matthew Mithra NoelShubham BharadwajVenkataraman Muthiah-NakarajanPraneet DuttaGeraldine Bessie AmaliPublished in: CoRR (2021)
Keyphrases
- activation function
- biologically inspired
- biologically plausible
- biological systems
- feed forward
- neural network
- hidden layer
- receptive fields
- artificial neural networks
- back propagation
- neural nets
- connection weights
- feed forward neural networks
- learning rate
- radial basis function
- visual cortex
- motor control
- hidden neurons
- network architecture
- multilayer perceptron
- multi layer perceptron
- spiking neural networks
- neural architecture
- learning rules
- fuzzy neural network
- training phase
- basis functions
- rbf neural network
- fuzzy logic
- learning algorithm
- high dimensional data
- fault diagnosis
- membership functions
- latent variables
- recurrent neural networks
- humanoid robot