Type inference methods based on deep learning are becoming increasingly
...
Transformer networks such as CodeBERT already achieve outstanding result...
Optional type annotations allow for enriching dynamic programming langua...
Automatic vulnerability detection on C/C++ source code has benefitted fr...
Learning from imprecise labels such as "animal" or "bird", but making pr...
Noisy data, crawled from the web or supplied by volunteers such as Mecha...
Large amounts of labeled training data are one of the main contributors ...
One of the most prominent problems in machine learning in the age of dee...
Knowledge transfer, zero-shot learning and semantic image retrieval are
...
The great success that deep models have achieved in the past is mainly o...
Neural networks and especially convolutional neural networks are of grea...
Classifying single image patches is important in many different applicat...