Hybrid memory cell unit and recurrent neural network including hybrid memory cell units

A recurrent neural network comprising:

• an input layer;
• a hidden layer;
• and
• an output layer,
• wherein the hidden layer comprises hybrid memory cell units, the hybrid memory cell units comprising:
• a plurality of first memory cells configured to remember a first cell state value fed back to each of gates to determine a degree to which each of the gates is open or closed, and configured to continue to update the first cell state value;
• and
• a plurality of second memory cells comprising a plurality of first time gates and a plurality of second time gates, the second plurality of memory cells being configured to remember a second cell state value,
• wherein each second memory cell of the plurality of second memory cells comprises a respective first time gate of the plurality of first time gates, the first time gate being configured to control the second cell state value of the second memory cell based on phase signals of an oscillatory frequency, and a respective second time gate of the plurality of second time gates, the second time gate being configured to control an output value of the second memory cell based on the phase signals.