The staggering innovations and emergence of numerous deep learning (DL) applications
have forced researchers to reconsider hardware architecture to accommodate fast and …

Deep neural networks have been applied in many applications exhibiting extraordinary
abilities in the field of computer vision. However, complex network architectures challenge …

Quantizing the activation, weight, and gradient to 4-bit is promising to accelerate neural
network training. However, existing 4-bit training methods require custom numerical formats …

Convolutional neural networks (CNNs) are used in our daily life, including self-driving cars,
virtual assistants, social network services, healthcare services, and face recognition, among …

(Frankle & Carbin, 2019) shows that there exist winning tickets (small but critical
subnetworks) for dense, randomly initialized networks, that can be trained alone to achieve …

The predominant paradigm for using machine learning models on a device is to train a
model in the cloud and perform inference using the trained model on the device. However …

The most important quality parameter of a product is its nutritional value, but marketability of
agricultural products depends primarily on the overall appearance and shape of the …

This paper proposes Mandheling, the first system that enables highly resource-efficient on-
device training by orchestrating mixed-precision training with on-chip Digital Signal …

Multiplication (eg, convolution) is arguably a cornerstone of modern deep neural networks
(DNNs). However, intensive multiplications cause expensive resource costs that challenge …

The wide adoption of deep neural networks has been accompanied by ever-increasing
energy and performance demands due to the expensive nature of training them. Numerous …