Красовская Софья Валерьевна
Deep-Learning Neural Nets as a Model of Saccadic Generation
Когнитивные науки и технологии: от нейрона к познанию
20 years ago, Laurent Itti and Christof Koch created a model of saliency in an attempt to recreate the work of biological pyramidal neurons by mimicking neurons with centre-surround receptive fields. The aim of the current study is to improve this model by using an artificial neural network that generates saccades similar to how humans make saccadic eye movements. The proposed model uses a Leaky Integrate-and-Fire layer for temporal predictions, and replaces parallel feature maps with a deep learning network in order to create a generative model, precise for both spatial and temporal predictions. Our deep neural network was able to predict eye movements based on unsupervised learning from raw images, as well as supervised learning from fixation maps retrieved during an eye-tracking experiment conducted with 35 participants at later stages in order to train a 2D softmax layer. The results imply that it is possible to match the spatial and temporal distributions of the model to corresponding human distributions.