In this work we provide new insights into the transformer architecture, ...
The automatic generation of medleys, i.e., musical pieces formed by diff...
We take a deep look into the behavior of self-attention heads in the
tra...
Explainability of deep learning systems is a vital requirement for many
...
Sharing knowledge between tasks is vital for efficient learning in a
mul...
Learning in sparse reward settings remains a challenge in Reinforcement
...
Drone delivery has been a hot topic in the industry in the past few year...
We introduce MIDI-VAE, a neural network model based on Variational
Autoe...
Deep generative models such as Variational Autoencoders (VAEs) and Gener...
We train multi-task autoencoders on linguistic tasks and analyze the lea...
We propose a novel approach for the generation of polyphonic music based...
The ability to use a 2D map to navigate a complex 3D environment is quit...