Non-linear Neurons with Human-like Apical Dendrite Activations
Preprint
Abstract
In order to classify linearly non-separable data, neurons are typically organized into multi-layer neural networks that are equipped with at least one hidden layer. Inspired by some recent discoveries in neuroscience, we propose a new model of artificial neuron along with a novel activation function enabling the learning of nonlinear decision boundaries using a single neuron. We show that a standard neuron followed by our novel apical dendrite activation (ADA) can learn the XOR logical function with 100% accuracy. Furthermore, we conduct experiments on six benchmark data sets from computer vision, signal processing and natural language processing, i.e. MOROCO, UTKFace, CREMA-D, Fashion-MNIST, Tiny ImageNet and ImageNet, showing that the ADA and the leaky ADA functions provide superior results to Rectified Linear Units (ReLU), leaky ReLU, RBF and Swish, for various neural network architectures, e.g. one-hidden-layer or two-hidden-layer multi-layer perceptrons (MLPs) and convolutional neural networks (CNNs) such as LeNet, VGG, ResNet and Character-level CNN. We obtain further performance improvements when we change the standard model of the neuron with our pyramidal neuron with apical dendrite activations (PyNADA). Our code is available at: https://github.com/raduionescu/pynada.Keywords
All Related Versions
This publication has 15 references indexed in Scilit:
- Activation functions in deep learning: A comprehensive survey and benchmarkNeurocomputing, 2022
- A survey on modern trainable activation functionsNeural Networks, 2021
- A survey of the recent architectures of deep convolutional neural networksArtificial Intelligence Review, 2020
- Training multi-layer spiking neural networks using NormAD based spatio-temporal error backpropagationNeurocomputing, 2020
- Deep appearance and motion learning for egocentric activity recognitionNeurocomputing, 2018
- Detecting anomalous events in videos by learning deep representations of appearance and motionComputer Vision and Image Understanding, 2017
- The Lure of the UnknownNeuron, 2006
- Gradient-based learning applied to document recognitionProceedings of the IEEE, 1998
- Learning representations by back-propagating errorsNature, 1986
- The perceptron: A probabilistic model for information storage and organization in the brain.Psychological Review, 1958