Deep neural networks (DNN) have demonstrated effectiveness for various applications such
as image processing, video segmentation, and speech recognition. Running state-of-theart …

Deploying state-of-the-art CNNs requires power-hungry processors and off-chip memory.
This precludes the implementation of CNNs in low-power embedded systems. Recent …

Deep Neural Networks (DNNs) have been adopted in many systems because of their higher
classification accuracy, with custom hardware implementations great candidates for high …

Our community has improved the efficiency of deep learning applications by exploiting
sparsity in inputs. Most of that work, though, is for inference, where weight sparsity is known …

Low bit-width Quantized Neural Networks (QNNs) enable deployment of complex machine
learning models on constrained devices such as microcontrollers (MCUs) by reducing their …

For deep-neural-network (DNN) processors [1-4], the product-sum (PS) operation
predominates the computational workload for both convolution (CNVL) and fully-connect …

We live in a world where technological advances are continually creating more data than
what we can deal with. Machine learning algorithms, in particular Deep Neural Networks …

Deep learning has revolutionized computer vision and other fields since its big bang in
2012. However, it is challenging to deploy Deep Neural Networks (DNNs) into real-world …

The number of parameters in deep neural networks (DNNs) is rapidly increasing to support
complicated tasks and to improve model accuracy. Correspondingly, the amount of …

This work exploits the tolerance of Deep Neural Networks (DNNs) to reduced precision
numerical representations and specifically, their recently demonstrated ability to tolerate …