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

<div>Absolute error given by using the approximated functions rather than of the original ones.</div>

Computational Intelligence and Neuroscience

fig5

Figure 5

Figure 5: [Retracted] A Post-training Quantization Method for the Design of Fixed-Point-Based FPGA/ASIC Hardware Accelerators for LSTM/GRU Algorithms 

Figure 5 | [Retracted] A Post-training Quantization Method for the Design of Fixed-Point-Based FPGA/ASIC Hardware Accelerators for LSTM/GRU Algorithms 