Skip to main content
Fig. 1 | BMC Neuroscience

Fig. 1

From: 27th Annual Computational Neuroscience Meeting (CNS*2018): Part Two

Fig. 1

(a) Sample environment with three landmarks. The arrows indicate the relationships encoded by the model after traversing the environment. (b) Illustration of per-module computation of relative locations as the subtraction of pairwise landmark locations after visiting all three locations. (c) A diagram showing the model layers and information flow. (d) Chart of the accuracy of the model on 1000 randomly generated environments as a function of noise (noise is measured as the number of landmarks replaced with a random landmark from the pool). Accuracy is compared against an ideal model and a bag-of-features (BOF) model

Back to article page