yesunhuang/QRNNs_Memory

For studying the memory and performance of Quantum Recurrent Neural Networks (QRNNs)

QRNNs_Memory

For studying the memory and performance of Quantum Recurrent Neural Networks (QRNNs)

Reference Paper

• For Modified Cuckoo Search (MCS)

  Walton, S., et al. "Modified cuckoo search: a new gradient free optimisation algorithm." Chaos, Solitons & Fractals 44.9 (2011): 710-718.

• For Quantum Reservoir Computation

  Fujii, Keisuke, and Kohei Nakajima. "Quantum reservoir computing: a reservoir approach toward quantum machine learning on near-term quantum devices." Reservoir Computing. Springer, Singapore, 2021. 423-450.

• For physical implement and simulation

  Bravo, Rodrigo Araiza, et al. "Quantum reservoir computing using arrays of Rydberg atoms." arXiv preprint arXiv:2111.10956 (2021).

Current Status

• The MCS optimizer for QNNs has been built and works well.
  1. Gradient Free
  2. Noise Resistance
  3. Pytorch Compatible
  4. Universal
• The Henon map data generator has been built and works well.
  1. Pytorch Compatible
  2. Iterator and DataLoader available
  3. Data saving and loading available
  4. Long time memory test available
• The classical RNNs have been built and tested.
  1. Pytorch Compatible
  2. All variances implemented in one class
  3. Typical sRNN works well
  4. Classical counterpart sucks.