Performance of biologically grounded models of the early visual system on standard object recognition tasks
| Autor: | René Larisch, Michael Teichmann, Fred H. Hamker |
|---|---|
| Rok vydání: | 2021 |
| Předmět: |
Computer science
Cognitive Neuroscience Models Neurological ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION Machine learning computer.software_genre Learning plasticity and memory Artificial Intelligence medicine Visual Cortex Neurons Computational Neuroscience Spiking neural network Neuronal Plasticity Computational neuroscience Artificial neural network business.industry Codebook Cognitive neuroscience of visual object recognition ComputingMethodologies_PATTERNRECOGNITION Hebbian theory Visual cortex medicine.anatomical_structure Visual Perception Neural Networks Computer Artificial intelligence business computer MNIST database |
| Zdroj: | Neural Networks. 144:210-228 |
| ISSN: | 0893-6080 |
| DOI: | 10.1016/j.neunet.2021.08.009 |
| Popis: | Computational neuroscience models of vision and neural network models for object recognition are often framed by different research agendas. Computational neuroscience mainly aims at replicating experimental data, while (artificial) neural networks target high performance on classification tasks. However, we propose that models of vision should be validated on object recognition tasks. At some point, mechanisms of realistic neuro-computational models of the visual cortex have to convince in object recognition as well. In order to foster this idea, we report the recognition accuracy for two different neuro-computational models of the visual cortex on several object recognition datasets. The models were trained using unsupervised Hebbian learning rules on natural scene inputs for the emergence of receptive fields comparable to their biological counterpart. We assume that the emerged receptive fields result in a general codebook of features, which should be applicable to a variety of visual scenes. We report the performances on datasets with different levels of difficulty, ranging from the simple MNIST to the more complex CIFAR-10 or ETH-80. We found that both networks show good results on simple digit recognition, comparable with previously published biologically plausible models. We also observed that our deeper layer neurons provide for naturalistic datasets a better recognition codebook. As for most datasets, recognition results of biologically grounded models are not available yet, our results provide a broad basis of performance values to compare methodologically similar models. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|
Full Text from ScienceDirect