Quantization scale and bit-width are the most important parameters when
...
The ability to accurately predict deep neural network (DNN) inference
pe...
When considering post-training quantization, prior work has typically fo...
Is it possible to restructure the non-linear activation functions in a d...
Autonomous systems are highly vulnerable to a variety of adversarial att...
With the advent of smart devices that support 4K and 8K resolution, Sing...
Executing machine learning workloads locally on resource constrained
mic...
Sequence model based NLP applications can be large. Yet, many applicatio...
Matrix multiplications between asymmetric bit-width operands, especially...
The open-source and community-supported gem5 simulator is one of the mos...
MobileNets family of computer vision neural networks have fueled tremend...
Recurrent Neural Networks (RNN) can be difficult to deploy on resource
c...
Recurrent neural networks can be large and compute-intensive, yet many
a...
Recurrent Neural Networks (RNN) can be large and compute-intensive, maki...
Machine learning-based applications are increasingly prevalent in IoT
de...