A Mixed-Precision Binary Neural Network Architecture for Touch Modality Classification
Konferenz: SMACD / PRIME 2021 - International Conference on SMACD and 16th Conference on PRIME
19.07.2021 - 22.07.2021 in online
Tagungsband: SMACD / PRIME 2021
Seiten: 4Sprache: EnglischTyp: PDF
Autoren:
Younes, Hamoud; Ibrahim, Ali (COSMIC Laboratory, Department of Electrical, Electronic and Telecommunications Engineering and Naval Architecture, University of Genova, Genoa, Italy, Genoa, Italy & Department of Computer and Communication Engineering, Lebanese International University, Bekaa, Lebanon)
Rizk, Mostafa (Department of Computer and Communication Engineering, Lebanese International University, Bekaa, Lebanon & Department of Physics and Electronics, Faculty of Sciences, Lebanese University, Lebanon)
Valle, Maurizio (COSMIC Laboratory, Department of Electrical, Electronic and Telecommunications Engineering and Naval Architecture, University of Genova, Genoa, Italy)
Inhalt:
Binary Neural Networks (BNN) have been proposed to address the computational complexity and memory requirements of Convolutional Neural Networks (CNN). However, in most of the applications, BNNs suffer from severe accuracy loss due to the 1-bit quantization. In this paper, a Mixed-Precision Binary Weight Network (MP-BWN) is proposed as a compromise between CNN and BNN. Compared to traditional binary networks, MP-BWN offers better performance with an acceptable increase in the network size. MP-BWN achieves up to 99% reduction in both the number of operations and the network size compared to similar state-of-the-art solutions. When validated on a touch modality classification problem, the MP-BWN surpassed similar existing solutions by achieving a classification accuracy of 77.8%.