This study provides a comprehensive review of the utilization of Virtual...
Using backpropagation to compute gradients of objective functions for
op...
Recent work in deep learning focuses on solving physical systems in the
...
This work proposes a Neural Network model that can control its depth usi...
Continuous medical time series data such as ECG is one of the most compl...
There is an analogy between the ResNet (Residual Network) architecture f...
Neural differential equations are a promising new member in the neural
n...
Informative missingness is unavoidable in the digital processing of
cont...
In this paper we present a lock-free version of Hopscotch Hashing. Hopsc...
Classical reverse-mode automatic differentiation (AD) imposes only a sma...
The deep learning community has devised a diverse set of methods to make...
DiffSharp is an algorithmic differentiation or automatic differentiation...
We show that Automatic Differentiation (AD) operators can be provided in...
Heretofore, automatic checkpointing at procedure-call boundaries, to red...
In this paper we introduce DiffSharp, an automatic differentiation (AD)
...
Automatic differentiation---the mechanical transformation of numeric com...