In 2017, Vaswani et al. proposed a new neural network architecture named Transformer. That modern architecture quickly revolutionized the natural language processing world. Models like GPT and BERT relying on this Transformer architecture have fully outperformed the previous state-of-theart networks. It surpassed the earlier approaches by such a wide margin that all the recent cutting edge models seem to rely on these Transformer-based architectures. In this paper, we provide an overview and explanations of the latest models. We cover the auto-regressive models such as GPT, GPT-2 and XLNET, as well as the auto-encoder architecture such as BERT and a lot of post-BERT models like RoBERTa, ALBERT, ERNIE 1.0/2.0.
Abstract:The Senior Living Lab (SLL) is a transdisciplinary research platform created by four Universities that aims at promoting ageing well at home through the co-creation of innovative products, services and practices with older adults. While most living labs for ageing well are focused on Information and Communication Technologies (ICTs), this social laboratory adopts a transdisciplinary approach, bringing together designers, economists, engineers and healthcare professionals to develop multiple forms of social innovation using participatory methods. The SLL is based on an ecological approach, connecting professionals and users in a cooperative network and involving all of the stakeholders concerned with ageing well, such as existing associations, business entities and policy-makers. Three main themes for the co-design of products and services were identified at the beginning of the SLL conception, each sustained by a major business partner: healthy nutrition to cope with frailty, improved autonomous mobility to foster independence and social communication to prevent isolation. This article shows the innovative transdisciplinary approach of the SLL and discusses the particular challenges that emerged during the first year of its creation, investigating the role of ICTs when designing products and services for older adults.
We report on the creation of a database of appliance consumption signatures and two test protocols to be used for appliance recognition tasks. By means of plug-based lowend sensors measuring the electrical consumption at low frequency, typically every 10 seconds, we made two acquisition sessions of one hour on about 100 home appliances divided into 10 categories: mobile phones (via chargers), coffee machines, computer stations (including monitor), fridges and freezers, Hi-Fi systems (CD players), lamp (CFL), laptops (via chargers), microwave oven, printers, and televisions (LCD or LED). We measured their consumption in terms of real power (W), reactive power (var), RMS current (A) and phase of voltage relative to current (ϕ). We now give free access to this ACS-F1 database. The proposed test protocols will help the scientific community to objectively compare new algorithms.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.