Note on the Reliability of Biological vs. Artificial Neural Networks
Open Access
- 12 February 2021
- journal article
- research article
- Published by Frontiers Media SA in Frontiers in Physiology
Abstract
Various types of neural networks are currently widely used in diverse technical applications, not least because neural networks are known to be able to “generalize.” The latter property raises expectations that they should be able to handle unexpected situations with similar success than humans. Using fundamental examples, we show that in situations for which they have not been trained, artificial approaches tend to run into substantial problems, which highlights a deficit in comparisons to human abilities. For this problem–which seems to have obtained little attention so far–we provide a first analysis, based on simple examples, which exhibits some key features responsible for the difference between human and artificial intelligence.Keywords
This publication has 13 references indexed in Scilit:
- Mammalian cochlea as a physics guided evolution-optimized hearing sensorScientific Reports, 2015
- Natural selection: A concept in need of some evolution?Complexity, 2011
- Evolution of Genome Size and Complexity in PinusPLOS ONE, 2009
- The Basic Gene Expression AlgorithmPublished by Springer Science and Business Media LLC ,2006
- Integrated Genomic and Proteomic Analyses of a Systematically Perturbed Metabolic NetworkScience, 2001
- Nucleotypic effects without nuclei: Genome size and erythrocyte size in mammalsGenome, 2000
- Approximation capabilities of multilayer feedforward networksNeural Networks, 1991
- Approximation by superpositions of a sigmoidal functionMathematics of Control, Signals, and Systems, 1989
- Size and shape of the cerebral cortex in mammals. I. The cortical surface.1985
- Size and Shape of the Cerebral Cortex in MammalsBrain, Behavior and Evolution, 1985