People with autism spectrum disorder (ASD) tend to detect lo- cal patterns of visual stimuli more quickly than global patterns, which is opposite to the behavior of typically developing peo- ple. We hypothesized that the imbalance between excitation and inhibition neurons in the visual cortex causes the local pro- cessing bias observed in ASD. Stronger inhibitory connections could diminish the neural activities and thus prevent global fea- ture integration, whereas properly balanced connections would enable the cortex to detect features of any size. We verified our hypothesis by employing a computational neural network called a neocognitron. Our experimental results demonstrated that the network with stronger inhibitory connections exhib- ited a local processing bias, whereas the network with properly adjusted connections showed a moderate global bias. More- over, the networks with extremely strong or weak inhibitions revealed no perception bias. These results suggest that an ex- citation/inhibition imbalance causes multiple types of atypical perception in ASD.