École Polytechnique Fédérale de Lausanne

About: École Polytechnique Fédérale de Lausanne is a facility organization based out in Lausanne, Switzerland. It is known for research contribution in the topics: Population & Catalysis. The organization has 44041 authors who have published 98296 publications receiving 4372092 citations. The organization is also known as: EPFL & ETHL.

Unsupervised Learning of Sentence Embeddings using Compositional n-Gram Features

Abstract: The recent tremendous success of unsupervised word embeddings in a multitude of applications raises the obvious question if similar methods could be derived to improve embeddings (i.e. semantic representations) of word sequences as well. We present a simple but efficient unsupervised objective to train distributed representations of sentences. Our method outperforms the state-of-the-art unsupervised models on most benchmark tasks, highlighting the robustness of the produced general-purpose sentence embeddings.

Mobile Subsurface Colloids and Their Role in Contaminant Transport

Abstract: Publisher Summary It is noted that colloidal particles can be effectively transported through subsurface porous media under certain hydrogeochemical conditions. If present in large concentrations, mobile colloids can act as carriers for strongly sorbing contaminants and thereby provide an unretarded transport pathway for contaminants that are otherwise strongly retarded. This potential transport pathway can be considered in risk assessments of sites heavily contaminated with toxic chemicals, such as certain radionuclides, heavy metals, and hydrophobic organic compounds. The chapter reviews the current state of knowledge about the behavior of colloids in porous media and their role in contaminant transport. The chapter also identifies some important future research needs. Colloids are commonly defined as small particles or other entities with dimensions roughly between 1 nm and 1 μm. These size limits to dissolved molecules on one side and to larger suspended particles on the other side. Colloidal particles remain stable in suspension over long time periods, unless they coagulate to form larger aggregates or deposit onto surfaces of larger grains.

What is Intrinsic Motivation? A Typology of Computational Approaches.

Abstract: Intrinsic motivation, the causal mechanism for spontaneous exploration and curiosity, is a central concept in developmental psychology. It has been argued to be a crucial mechanism for open-ended cognitive development in humans, and as such has gathered a growing interest from developmental roboticists in the recent years. The goal of this paper is threefold. First, it provides a synthesis of the different approaches of intrinsic motivation in psychology. Second, by interpreting these approaches in a computational reinforcement learning framework, we argue that they are not operational and even sometimes inconsistent. Third, we set the ground for a systematic operational study of intrinsic motivation by presenting a formal typology of possible computational approaches. This typology is partly based on existing computational models, but also presents new ways of conceptualizing intrinsic motivation. We argue that this kind of computational typology might be useful for opening new avenues for research both in psychology and developmental robotics.

Collecting complex activity datasets in highly rich networked sensor environments

Abstract: We deployed 72 sensors of 10 modalities in 15 wireless and wired networked sensor systems in the environment, in objects, and on the body to create a sensor-rich environment for the machine recognition of human activities. We acquired data from 12 subjects performing morning activities, yielding over 25 hours of sensor data. We report the number of activity occurrences observed during post-processing, and estimate that over 13000 and 14000 object and environment interactions occurred. We describe the networked sensor setup and the methodology for data acquisition, synchronization and curation. We report on the challenges and outline lessons learned and best practice for similar large scale deployments of heterogeneous networked sensor systems. We evaluate data acquisition quality for on-body and object integrated wireless sensors; there is less than 2.5% packet loss after tuning. We outline our use of the dataset to develop new sensor network self-organization principles and machine learning techniques for activity recognition in opportunistic sensor configurations. Eventually this dataset will be made public.