In the neural Turing machine (NTM), the content-based addressing and location-based addressing is used for memory addressing. Content-based addressing is similar to the attention-based model, weighting each row of memory which shows the importance of each row of memory (or each location of memory). Then for location-based addressing, by using shift kernel, the attention focus is moved left or right or remains unchanged.
What is location-based addressing? Why was location-based addressing used? What is the concept of "for location-based addressing, by using shift kernel, the attention focus is moved left or right or remains unchanged."? What is the difference between content-based addressing and location-based addressing?
