Transformations based on domain expertise (expert transformations), such...
Model stitching (Lenc Vedaldi 2015) is a compelling methodology to c...
Deep ensembles (DE) have been successful in improving model performance ...
Studying the dynamics of open quantum systems holds the potential to ena...
Finding efficient optimization methods plays an important role for quant...
State-of-the-art (SOTA) semi-supervised learning (SSL) methods have been...
In social science, formal and quantitative models, such as ones describi...
Conservation laws are key theoretical and practical tools for understand...
Recent advances in deep learning, in particular enabled by hardware adva...
Deep learning techniques have been increasingly applied to the natural
s...
The emergence of unsupervised word embeddings, pre-trained on very large...
A key factor in the modern success of deep learning is the astonishing
e...
We present a logarithmic-scale efficient convolutional neural network
ar...
The concepts of unitary evolution matrices and associative memory have
b...