[Retracted] A Post-training Quantization Method for the Design of Fixed-Point-Based FPGA/ASIC Hardware Accelerators for LSTM/GRU Algorithms

<div>Approximated linear activation functions.</div>

Computational Intelligence and Neuroscience

fig4

Figure 4

Figure 4: [Retracted] A Post-training Quantization Method for the Design of Fixed-Point-Based FPGA/ASIC Hardware Accelerators for LSTM/GRU Algorithms 

Figure 4 | [Retracted] A Post-training Quantization Method for the Design of Fixed-Point-Based FPGA/ASIC Hardware Accelerators for LSTM/GRU Algorithms 