Recent Advances
Recently Published Documents


(FIVE YEARS 19581)



2022 ◽  
Vol 73 ◽  
pp. 290-299
Kai Weißenbruch ◽  
Enrico D Lemma ◽  
Marc Hippler ◽  
Martin Bastmeyer

2022 ◽  
Vol 54 (8) ◽  
pp. 1-34
Fuqiang Gu ◽  
Mu-Huan Chung ◽  
Mark Chignell ◽  
Shahrokh Valaee ◽  
Baoding Zhou ◽  

Human activity recognition is a key to a lot of applications such as healthcare and smart home. In this study, we provide a comprehensive survey on recent advances and challenges in human activity recognition (HAR) with deep learning. Although there are many surveys on HAR, they focused mainly on the taxonomy of HAR and reviewed the state-of-the-art HAR systems implemented with conventional machine learning methods. Recently, several works have also been done on reviewing studies that use deep models for HAR, whereas these works cover few deep models and their variants. There is still a need for a comprehensive and in-depth survey on HAR with recently developed deep learning methods.

2021 ◽  
Vol 252 ◽  
pp. 109901
Yan Cao ◽  
Nai-Yuan Xu ◽  
Alibek Issakhov ◽  
Abdol Ghaffar Ebadi ◽  
Mohammad Reza Poor Heravi ◽  

2021 ◽  
Vol 5 (OOPSLA) ◽  
pp. 1-25
Gust Verbruggen ◽  
Vu Le ◽  
Sumit Gulwani

The ability to learn programs from few examples is a powerful technology with disruptive applications in many domains, as it allows users to automate repetitive tasks in an intuitive way. Existing frameworks on inductive synthesis only perform syntactic manipulations, where they rely on the syntactic structure of the given examples and not their meaning. Any semantic manipulations, such as transforming dates, have to be manually encoded by the designer of the inductive programming framework. Recent advances in large language models have shown these models to be very adept at performing semantic transformations of its input by simply providing a few examples of the task at hand. When it comes to syntactic transformations, however, these models are limited in their expressive power. In this paper, we propose a novel framework for integrating inductive synthesis with few-shot learning language models to combine the strength of these two popular technologies. In particular, the inductive synthesis is tasked with breaking down the problem in smaller subproblems, among which those that cannot be solved syntactically are passed to the language model. We formalize three semantic operators that can be integrated with inductive synthesizers. To minimize invoking expensive semantic operators during learning, we introduce a novel deferred query execution algorithm that considers the operators to be oracles during learning. We evaluate our approach in the domain of string transformations: the combination methodology can automate tasks that cannot be handled using either technologies by themselves. Finally, we demonstrate the generality of our approach via a case study in the domain of string profiling.

2021 ◽  
Vol 5 (OOPSLA) ◽  
pp. 1-31
Wolf Honoré ◽  
Jieung Kim ◽  
Ji-Yong Shin ◽  
Zhong Shao

Despite recent advances, guaranteeing the correctness of large-scale distributed applications without compromising performance remains a challenging problem. Network and node failures are inevitable and, for some applications, careful control over how they are handled is essential. Unfortunately, existing approaches either completely hide these failures behind an atomic state machine replication (SMR) interface, or expose all of the network-level details, sacrificing atomicity. We propose a novel, compositional, atomic distributed object (ADO) model for strongly consistent distributed systems that combines the best of both options. The object-oriented API abstracts over protocol-specific details and decouples high-level correctness reasoning from implementation choices. At the same time, it intentionally exposes an abstract view of certain key distributed failure cases, thus allowing for more fine-grained control over them than SMR-like models. We demonstrate that proving properties even of composite distributed systems can be straightforward with our Coq verification framework, Advert, thanks to the ADO model. We also show that a variety of common protocols including multi-Paxos and Chain Replication refine the ADO semantics, which allows one to freely choose among them for an application's implementation without modifying ADO-level correctness proofs.

2021 ◽  
Vol 101 ◽  
pp. 108176
Chen-Chen Sun ◽  
Zuo-qiong Zhou ◽  
Dong Yang ◽  
Zhang-lin Chen ◽  
Yun-yi Zhou ◽  

2022 ◽  
Vol 450 ◽  
pp. 214240
Guilong Lu ◽  
Feng Chu ◽  
Xiubing Huang ◽  
Yaqiong Li ◽  
Kaiyan Liang ◽  

2021 ◽  
Vol 54 ◽  
pp. 101760
María L. Goñi ◽  
Nicolás A. Gañán ◽  
Raquel E. Martini

2021 ◽  
Vol 7 ◽  
pp. 6581-6599
Pragya Gawhade ◽  
Amit Ojha

2021 ◽  
Vol 44 ◽  
pp. 103322
Mohammad Nazmus Sakib ◽  
Saifuddin Ahmed ◽  
S. M. Sultan Mahmud Rahat ◽  
Sanzeeda Baig Shuchi

Sign in / Sign up

Export Citation Format

Share Document