Publications associées à Google DeepMind

Crowd-Robot Interaction: Crowd-aware Robot Navigation with Attention-based Deep Reinforcement Learning

Alexandre Massoud Alahi, Yuejiang Liu, Sven Kreiss, Changan Chen

Mobility in an effective and socially-compliant manner is an essential yet challenging task for robots operating in crowded spaces. Recent works have shown the power of deep reinforcement learning techniques to learn socially cooperative policies. However, ...

IEEE2019

CityLearn v1.0: An OpenAI Gym Environment for Demand Response with Deep Reinforcement Learning

Jérôme Henri Kämpf

Demand response has the potential of reducing peaks of electricity demand by about 20% in the US, where buildings represent roughly 70% of the total electricity demand. Buildings are dynamic systems in constant change (i.e. occupants' behavior, refurbishme ...

ACM2019

3D-Stacked CMOS SPAD Image Sensors: Technology and Applications

Edoardo Charbon, Claudio Bruschini, Myung Jae Lee

3Dstacked CMOS SPAD based image sensors hold the promise for better sensitivity and more functionality per pixel. The technology enables to separate detection from computation onto different chips, or tiers, that are stacked onto one another. One advantage ...

IEEE2018

Deep Learning for Logic Optimization Algorithms, 2018 IEEE International Symposium on Circuits and Systems (ISCAS)

Giovanni De Micheli, Sabine Süsstrunk, Frédéric Kaplan, Mathias Soeken, Winston Jason Haaswijk, Benoît Laurent Auguste Seguin, Edo Collins

The slowing down of Moore's law and the emergence of new technologies puts an increasing pressure on the field of EDA. There is a constant need to improve optimization algorithms. However, finding and implementing such algorithms is a difficult task, espec ...

2018

Deep Learning for Logic Optimization Algorithms

Giovanni De Micheli, Sabine Süsstrunk, Frédéric Kaplan, Mathias Soeken, Winston Jason Haaswijk, Benoît Laurent Auguste Seguin, Edo Collins

The slowing down of Moore's law and the emergence of new technologies puts an increasing pressure on the field of EDA. There is a constant need to improve optimization algorithms. However, finding and implementing such algorithms is a difficult task, espec ...

IEEE2018

Deep Learning Works in Practice. But Does it Work in Theory?

Rachid Guerraoui, Le Nguyen Hoang

Deep learning relies on a very specific kind of neural networks: those superposing several neural layers. In the last few years, deep learning achieved major breakthroughs in many tasks such as image analysis, speech recognition, natural language processin ...

2018

CONTEXT-AWARE ATTENTION MECHANISM FOR SPEECH EMOTION RECOGNITION

Philip Neil Garner, Gaétan Ramet

In this work, we study the use of attention mechanisms to enhance the performance of the state-of-the-art deep learning model in Speech Emotion Recognition (SER). We introduce a new Long Short-Term Memory (LSTM)-based neural network attention model which i ...

IEEE2018

A Domain-Adaptive Two-Stream U-Net for Electron Microscopy Image Segmentation

Pascal Fua, Mathieu Salzmann, Pablo Marquez Neila, Róger Bermúdez Chacón

Deep networks such as the U-Net are outstanding at segmenting biomedical images when enough training data is available, but only then. Here we introduce a Domain Adaptation approach that relies on two coupled U-Nets that either regularize or share correspo ...

2018

A Domain-Adaptive Two-Stream U-Net For Electron Microscopy Image Segmentation

Pascal Fua, Mathieu Salzmann, Pablo Marquez Neila

Deep networks such as the U-Net are outstanding at segmenting biomedical images when enough training data is available, but only then. Here we introduce a Domain Adaptation approach that relies on two coupled U-Nets that either regularize or share correspo ...

IEEE2018

Target Detection with Deep Learning in Polarimetric Imaging

Selman Ergünay, Yusuf Leblebici, Süha Kagan Köse

Polarimetric imaging techniques demonstrate enhanced capabilities in advanced object detection tasks with their capability to discriminate man-made objects from natural background surfaces. While spectral signatures carry information only about material pr ...

SPIE-INT SOC OPTICAL ENGINEERING2018

Google DeepMind

Crowd-Robot Interaction: Crowd-aware Robot Navigation with Attention-based Deep Reinforcement Learning

CityLearn v1.0: An OpenAI Gym Environment for Demand Response with Deep Reinforcement Learning

3D-Stacked CMOS SPAD Image Sensors: Technology and Applications

Deep Learning for Logic Optimization Algorithms, 2018 IEEE International Symposium on Circuits and Systems (ISCAS)

Deep Learning for Logic Optimization Algorithms

Deep Learning Works in Practice. But Does it Work in Theory?

CONTEXT-AWARE ATTENTION MECHANISM FOR SPEECH EMOTION RECOGNITION

A Domain-Adaptive Two-Stream U-Net for Electron Microscopy Image Segmentation

A Domain-Adaptive Two-Stream U-Net For Electron Microscopy Image Segmentation

Target Detection with Deep Learning in Polarimetric Imaging

Graph Chatbot

Chattez avec Graph Search

A Domain-Adaptive Two-Stream U-Net For Electron Microscopy Image Segmentation

Crowd-Robot Interaction: Crowd-aware Robot Navigation with Attention-based Deep Reinforcement Learning

Deep Learning for Logic Optimization Algorithms

Deep Learning for Logic Optimization Algorithms, 2018 IEEE International Symposium on Circuits and Systems (ISCAS)

Target Detection with Deep Learning in Polarimetric Imaging

Deep Learning Works in Practice. But Does it Work in Theory?

CONTEXT-AWARE ATTENTION MECHANISM FOR SPEECH EMOTION RECOGNITION

A Domain-Adaptive Two-Stream U-Net for Electron Microscopy Image Segmentation

CityLearn v1.0: An OpenAI Gym Environment for Demand Response with Deep Reinforcement Learning

3D-Stacked CMOS SPAD Image Sensors: Technology and Applications