Neural Networks with Cerebrum Functions Can Exchange Knowledge by Dialog

We can talk about not only the topics in front of us, but also the topics of the past and the future. We are discussing while confirming each other's imagination and understanding. Even in the era when humans did not have letters, they negotiated the exchange of goods, gained new knowledge, and expanded their living area. Of course, using letters further developed civilization to the present day. The group of humans is called society, and the ability to dialogue is essential to be a member of that group. What are the functions required for dialogue ability? This is the starting point of this paper. Trained livestock can understand how to act with the owner's commands or gestures. However, it is not possible to return messages to the owner, such as having leftover work or interruption of work due to inconvenient work etc. This message is the language itself that shows the ability to dialogue. This paper shows that to enable two-way dialogue, both brains need two areas related to language. One area consists of the time series of symbols, and the other area consists of images activated by responses from the symbol area. This structure and behavior are consistent with the knowledge of Cerebrum in neuroscience. The basic logical circuits of neural networks follow Hebb's law in neuroscience, and by connecting them hierarchically, arbitrary logical circuits can be realized with limited scale.