Associative LSTM
2000년 도입 · 논문 1편에서 사용
An Associative LSTM combines an LSTM with ideas from Holographic Reduced Representations (HRRs) to enable key-value storage of data. HRRs use a “binding” operator to implement key-value binding between two vectors (the key and its associated content). They natively implement associative arrays; as a byproduct, they can also easily implement stacks, queues, or lists.
출처: Associative Long Short-Term Memory
소개 논문: Associative Long Short-Term Memory
Recurrent Neural Networks · Sequential