We present a 3.1 POp/s/W fully digital hardware accelerator for ternary neural networks
(TNNs). CUTIE, the completely unrolled ternary inference engine, focuses on minimizing …

Ternary neural networks (TNNs) offer a superior accuracy-energy tradeoff compared to
binary neural networks. However, until now, they have required specialized accelerators to …

Embodied AI requires pushing complex multi-modal models to the extreme edge for time-
constrained tasks such as autonomous navigation of robots and vehicles. On small form …

Since the breakthrough success of AlexNet in the ILSVRC image recognition challenge in
2012, Deep Neural Networks (DNNs), and in particular Convolutional Neural Networks …

We introduce Kraken, a highly flexible heterogeneous system-on-chip (SoC) fabricated in 22
FDX technology demonstrating leading-edge energy efficiency and computational …

Digital computation using ternary logic allows compact and energy-efficient digital design
due to the reduction in circuit interconnects and chip area. CNFET unique characteristic of …

Zeitgleich mit der rasanten Ausbreitung des Internet of Things (IoT) hat die Entwicklung von
Deep-Learning-Algorithm eine Revolution im Feld des maschinellen Lernens ausgelöst. Die …

Ternary logic theory and CNTFETs The basic theory of ternary logic and CNTFETs are
explored and explained, to set a theoretical context and build a base for the rest of the …

With the surging popularity of edge computing, the need to efficiently perform neural network
inference on battery-constrained IoT devices has greatly increased. While algorithmic …

Convolutional neural networks (CNNs) have achieved great successes in various domains
of artificial intelligence, but they require large amounts of memory and computational power …