Shallow Unorganized Neural Networks using Smart Neuron Model for Visual Perception
Preprint
Abstract
The recent success of Deep Neural Networks (DNNs) has revealed the significant capability of neural computing in many challenging applications. Although DNNs are derived from emulating biological neurons, there still exist doubts over whether or not DNNs are the final and best model to emulate the mechanism of human intelligence. In particular, there are two discrepancies between computational DNN models and the observed facts of biological neurons. First, human neurons are interconnected randomly, while DNNs need carefully-designed architectures to work properly. Second, human neurons usually have a long spiking latency (~100ms) which implies that not many layers can be involved in making a decision, while DNNs could have hundreds of layers to guarantee high accuracy. In this paper, we propose a new computational model, namely shallow unorganized neural networks (SUNNs), in contrast to ANNs/DNNs. The proposed SUNNs differ from standard ANNs or DNNs in three fundamental aspects: 1) SUNNs are based on an adaptive neuron cell model, Smart Neurons, that allows each artificial neuron cell to adaptively respond to its inputs rather than carrying out a fixed weighted-sum operation like the classic neuron model in ANNs/DNNs; 2) SUNNs can cope with computational tasks with very shallow architectures; 3) SUNNs have a natural topology with random interconnections, as the human brain does, and as proposed by Turing's B-type unorganized machines. We implemented the proposed SUNN architecture and tested it on a number of unsupervised early stage visual perception tasks. Surprisingly, such simple shallow architectures achieved very good results in our experiments. The success of our new computational model makes it the first workable example of Turing's B-Type unorganized machine that can achieve comparable or better performance against the state-of-the-art algorithms.Keywords
All Related Versions
This publication has 25 references indexed in Scilit:
- Role for 2D image generated 3D face models in the rehabilitation of facial palsyHealthcare Technology Letters, 2017
- Mastering the game of Go with deep neural networks and tree searchNature, 2016
- A neuromorphic network for generic multivariate data classificationProceedings of the National Academy of Sciences, 2014
- Network hubs in the human brainTrends in Cognitive Sciences, 2013
- Accurate subpixel edge location based on partial area effectImage and Vision Computing, 2013
- Alan Turing’s unorganized machines and artificial neural networks: his remarkable early work and future possibilitiesEvolutionary Intelligence, 2011
- Sensitivity to perturbations in vivo implies high noise and suggests rate coding in cortexNature, 2010
- Regularized Laplacian Zero Crossings as Optimal Edge IntegratorsInternational Journal of Computer Vision, 2003
- Speed of processing in the human visual systemNature, 1996
- Learning representations by back-propagating errorsNature, 1986