First, we study the noise stability of such networks on unperturbed inputs and observe that internal activations of adversarially trained networks have lower Signal-to-Noise Ratio (SNR), and are sensitive to noise than vanilla networks.
The increasing computational demand of Deep Learning has propelled research in special-purpose inference accelerators based on emerging non-volatile memory (NVM) technologies.
The `Internet of Things' has brought increased demand for AI-based edge computing in applications ranging from healthcare monitoring systems to autonomous vehicles.
The spiking autoencoders are benchmarked on MNIST and Fashion-MNIST and achieve very low reconstruction loss, comparable to ANNs.
In this work, we propose extremely quantized hybrid network architectures with both binary and full-precision sections to emulate the classification performance of full-precision networks while ensuring significant energy efficiency and memory compression.
In this paper, we demonstrate how deep binary networks can be accelerated in modified von-Neumann machines by enabling binary convolutions within the SRAM array.
Over the past decade, Deep Convolutional Neural Networks (DCNNs) have shown remarkable performance in most computer vision tasks.