Abstract
In this paper, we present neuro-robotics models with a deep artificial neural network capable of generating finger counting positions and number estimation. We first train the model in an unsupervised manner where each layer is treated as a Restricted Boltzmann Machine or an autoencoder. Such a model is further trained in a supervised way. This type of pretraining is tested on our baseline model and two methods of pre-training are compared. The network is extended to produce finger counting positions. The performance in number estimation of such an extended model is evaluated. We test the hypothesis if the subitizing process can be obtained by one single model used also for estimation of higher numerosities. The results confirm the importance of unsupervised training in our enumeration task and show some similarities to human behaviour in the case of subitizing.
| Original language | English |
|---|---|
| Title of host publication | Proceedings of the 2019 IEEE Symposium Series on Computational Intelligence |
| Publication status | Accepted/In press - 1 Sept 2019 |
| Event | 2019 IEEE Symposium Series on Computational Intelligence: IEEE Symposium on Neuromorphic Cognitive Computing (IEEE SNCC) - Xiamen, China Duration: 6 Dec 2019 → 9 Dec 2019 http://ssci2019.org/sncc.html |
Conference
| Conference | 2019 IEEE Symposium Series on Computational Intelligence |
|---|---|
| Abbreviated title | IEEE SSCI 2019 |
| Country/Territory | China |
| City | Xiamen |
| Period | 6/12/19 → 9/12/19 |
| Internet address |