Quantum RNNs and LSTMs Through Entangling and Disentangling Power of Unitary Transformations
This work proposes a quantum-classical framework to guide the design of better-parameterized quantum circuits for real-world applications, but it appears incremental as it builds on prior knowledge without presenting new experimental results or benchmarks.
The paper tackles the problem of modeling quantum recurrent neural networks (RNNs) and LSTMs by interpreting the entangling and disentangling power of unitary transformations as information retention and forgetting mechanisms, with entanglement becoming a key component in the training process.
In this paper, we discuss how quantum recurrent neural networks (RNNs) and their enhanced version, long short-term memory (LSTM) networks, can be modeled using the core ideas presented in Ref.[1], where the entangling and disentangling power of unitary transformations is investigated. In particular, we interpret entangling and disentangling power as information retention and forgetting mechanisms in LSTMs. Therefore, entanglement becomes a key component of the optimization (training) process. We believe that, by leveraging prior knowledge of the entangling power of unitaries, the proposed quantum-classical framework can guide and help to design better-parameterized quantum circuits for various real-world applications.