Driven by the need for the compression of weights in neural networks (NNs), which is especially beneficial for edge devices with a constrained resource, and by the need to utilize the simplest possible quantization model, in this paper, we study the performance of three-bit post-training uniform quantization. The goal is to put various choices of the key parameter of the quantizer in question (support region threshold) in one place and provide a detailed overview of this choice’s impact on the performance of post-training quantization for the MNIST dataset. Specifically, we analyze whether it is possible to preserve the accuracy of the two NN models (MLP and CNN) to a great extent with the very simple three-bit uniform quantizer, regardless of the choice of the key parameter. Moreover, our goal is to answer the question of whether it is of the utmost importance in post-training three-bit uniform quantization, as it is in quantization, to determine the optimal support region threshold value of the quantizer to achieve some predefined accuracy of the quantized neural network (QNN). The results show that the choice of the support region threshold value of the three-bit uniform quantizer does not have such a strong impact on the accuracy of the QNNs, which is not the case with two-bit uniform post-training quantization, when applied in MLP for the same classification task. Accordingly, one can anticipate that due to this special property, the post-training quantization model in question can be greatly exploited.

No abstract

This research presents an audio coding scheme, based on sub-band coding (SBC), with the implementation of quasi-logarithmic compandors. The presented coding scheme is based on signal decomposition and individual processing of the different sub-bands. Two SBC schemes for audio coding are presented, a non-adaptive and an adaptive coding scheme. The application of backward adaptation technique further improves the performance of this coding scheme, especially when using smaller compression factor values. This paper also describes the determination of an efficient bit allocation, used for coding the individual sub-bands. The results indicate that the proposed coding schemes can successfully be implemented in audio signal coding, providing a high quality output signal.

No abstract

No abstract