Quantized neural networks employ reduced precision representations for both weights and
activations. This quantization process significantly reduces the memory requirements and …

Binary neural networks (BNNs) are variations of artificial/deep neural network (ANN/DNN)
architectures that constrain the real values of weights to the binary set of numbers {− 1, 1} …

Binarization is an extreme quantization technique that is attracting research in the Internet of
Things (IoT) field, as it radically reduces the memory footprint of deep neural networks …

Convolutional neural networks (CNN) have emerged as a dominant deep learning
technique in various fields, including image processing, computer vision, and intelligent …

Deep Hashing (DH) has emerged as an indispensable technique for fast image search in
recent years. To deploy DH on resource-limited devices, the Binary Neural Network (BNN) …

This work focuses on the efficient quantization of convolutional neural networks (CNNs).
Specifically, we introduce a method called non-uniform uniform quantization (NUUQ), a …

Quantization-aware training comes with a fundamental challenge: the derivative of
quantization functions such as rounding are zero almost everywhere and nonexistent …

This brief introduces a novel 1.57-Mb IMC architecture that utilizes emerging voltage-gated
spin-orbit torque magnetic random-access memory (VGSOT MRAM) device. Apart from …

Gyroscopes are widely used in navigation systems of ships and vehicles, stabilizing systems
for devices such as cameras and drones, robotic control systems, and orientation systems of …

Pruning and compression of models are practical approaches for deploying and applying
deep convolutional neural networks in scenarios with limited memory and computational …