Source-free domain adaptation (SFDA) is compelling because it allows ada...
The architecture and the parameters of neural networks are often optimiz...
Average-case analysis computes the complexity of an algorithm averaged o...
Graph neural networks have become increasingly popular in recent years d...
This work revisits the use of information criteria to characterize the
g...
We review the current state of automatic differentiation (AD) for array
...
The need to efficiently calculate first- and higher-order derivatives of...
Automatic differentiation (AD) is an essential primitive for machine lea...
We propose a generalization of neural network sequence models. Instead o...
Theano is a Python library that allows to define, optimize, and evaluate...
We introduce two Python frameworks to train neural networks on large
dat...
One long-term goal of machine learning research is to produce methods th...
The authors of (Cho et al., 2014a) have shown that the recently introduc...
In this paper, we propose a novel neural network model called RNN
Encode...