Quasi-Newton methods still face significant challenges in training
large...
We present decalf, a directed, effectful cost-aware logical framework fo...
We present two metalanguages for developing synthetic cost-aware
denotat...
Leveraging parallel hardware (e.g. GPUs) to conduct deep neural network ...
We present calf, a cost-aware
logical framework for studying quantitativ...
Although computational complexity is a fundamental aspect of program
beh...
To accelerate inference of Convolutional Neural Networks (CNNs), various...