“…However, these quantized neural networks suffer from accuracy loss, especially in big datasets. In the contribution by Nazari et al "E2BNet: MAC-Free yet accurate 2-level binarized neural network accelerator for embedded systems," authors introduce a quantized neural network with 2-bit weights and activations that are more accurate compared to the state-of-the-art quantized neural networks, and also the accuracy is close to the full precision neural network [10]. Moreover, the authors propose E2BNet, an efficient MAC-free hardware architecture that increases power efficiency and throughput/W about 3.6× and 1.5×, respectively, compared to the state-of-the-art quantized neural networks.…”