Hippocampal Anatomy Supports the Use of Context in Object Recognition: A Computational Model
Figure 5
Training and test sets. The training set consists of 120 objects and 40 contexts, with 3 objects per context. The test sets are the same as the training set, except with either noise added (additive or nonadditive noise), part of the pattern missing (partial cue), or an object and context mismatch.
