We have proposed a neural network model that stores the incoming information after orthogonalizing it in the same manner as vectors are orthogonalized. The scheme enables the brain to compare a new informational system with those in the memory and store its similarities and differences with the old memories in an economical manner. This allows the brain to have an enormous capacity and yet the retrieval can be very accurate and efficient. Examples of how the idea is applied to the acquisition of words in the mental lexicon, and discrimination of contexts of motor actions by the cerebellum will be discussed. We will also describe an extension of the model to study how the memory might cope with trauma.