Search Results for author: Gino Brunner

Found 12 papers, 7 papers with code

Of Non-Linearity and Commutativity in BERT

1 code implementation12 Jan 2021 Sumu Zhao, Damian Pascual, Gino Brunner, Roger Wattenhofer

In this work we provide new insights into the transformer architecture, and in particular, its best-known variant, BERT.

Inductive Bias

Medley2K: A Dataset of Medley Transitions

no code implementations25 Aug 2020 Lukas Faber, Sandro Luck, Damian Pascual, Andreas Roth, Gino Brunner, Roger Wattenhofer

The automatic generation of medleys, i. e., musical pieces formed by different songs concatenated via smooth transitions, is not well studied in the current literature.

Telling BERT's full story: from Local Attention to Global Aggregation

no code implementations EACL 2021 Damian Pascual, Gino Brunner, Roger Wattenhofer

This way, we propose a distinction between local patterns revealed by attention and global patterns that refer back to the input, and analyze BERT from both angles.

On Identifiability in Transformers

no code implementations ICLR 2020 Gino Brunner, Yang Liu, Damián Pascual, Oliver Richter, Massimiliano Ciaramita, Roger Wattenhofer

We show that, for sequences longer than the attention head dimension, attention weights are not identifiable.

Using State Predictions for Value Regularization in Curiosity Driven Deep Reinforcement Learning

1 code implementation30 Sep 2018 Gino Brunner, Manuel Fritsche, Oliver Richter, Roger Wattenhofer

Learning in sparse reward settings remains a challenge in Reinforcement Learning, which is often addressed by using intrinsic rewards.

reinforcement-learning

The Urban Last Mile Problem: Autonomous Drone Delivery to Your Balcony

1 code implementation21 Sep 2018 Gino Brunner, Bence Szebedy, Simon Tanner, Roger Wattenhofer

The drop-off location could, e. g., be on a balcony or porch, and simply needs to be indicated by a visual marker on the wall or window.

Robotics Systems and Control

Symbolic Music Genre Transfer with CycleGAN

5 code implementations20 Sep 2018 Gino Brunner, Yuyi Wang, Roger Wattenhofer, Sumu Zhao

In this paper we apply such a model to symbolic music and show the feasibility of our approach for music genre transfer.

Music Genre Transfer Style Transfer

MIDI-VAE: Modeling Dynamics and Instrumentation of Music with Applications to Style Transfer

no code implementations20 Sep 2018 Gino Brunner, Andres Konrad, Yuyi Wang, Roger Wattenhofer

The interpolations smoothly change pitches, dynamics and instrumentation to create a harmonic bridge between two music pieces.

Style Transfer

Natural Language Multitasking: Analyzing and Improving Syntactic Saliency of Hidden Representations

no code implementations18 Jan 2018 Gino Brunner, Yuyi Wang, Roger Wattenhofer, Michael Weigelt

We train multi-task autoencoders on linguistic tasks and analyze the learned hidden sentence representations.

Translation

Teaching a Machine to Read Maps with Deep Reinforcement Learning

1 code implementation20 Nov 2017 Gino Brunner, Oliver Richter, Yuyi Wang, Roger Wattenhofer

Localization and navigation is also an important problem in domains such as robotics, and has recently become a focus of the deep reinforcement learning community.

Navigate reinforcement-learning

Cannot find the paper you are looking for? You can Submit a new open access paper.