A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL.
The file type is application/pdf
.
Filters
Meta-Forecasting by combining Global Deep Representations with Local Adaptation
[article]
2021
arXiv
pre-print
We introduce a novel forecasting method, called Meta Global-Local Auto-Regression (Meta-GLAR), that adapts to each time series by learning in closed-form the mapping from the representations produced by ...
To bridge this gap, we adopt a meta-learning view of the time series forecasting problem. ...
predictions when applied to out-of-sample TS, potentially combining the inference speed and accuracy of deep learning models with the ease-of-use of classical local models. ...
arXiv:2111.03418v2
fatcat:3ljnuvvbufgwlitxdgbnz3tgiy
Online Multi-Object Tracking with Visual and Radar Features
2020
IEEE Access
To achieve it, we propose a unified MOT framework based on object model learning and confidence-based association. ...
We implement several MOT systems with different object model learning and association methods, and compare our system with them on challenging visual MOT datasets. ...
general, detections of a new track should not be associated with any existing tracks in the local and global association stages. ...
doi:10.1109/access.2020.2994000
fatcat:65ihpxygvffhbpkfsyu2jiifsy
Koopman Neural Forecaster for Time Series with Temporal Distribution Shifts
[article]
2023
arXiv
pre-print
KNF imposes appropriate inductive biases for improved robustness against distributional shifts, employing both a global operator to learn shared characteristics and a local operator to capture changing ...
the coefficients of chosen measurement functions. ...
Department Of Energy, Office of Science, U. S. Army Research Office under Grant W911NF-20-1-0334, and NSF Grants #2134274, #2107256 and #2134178. ...
arXiv:2210.03675v3
fatcat:hmorvj3k6zbffhako6o32qt7vu
Local models-based regression trees for very short-term wind speed prediction
2015
Renewable Energy
In this paper we comparatively evaluate eight different types of RTs algorithms, and we show that they are able obtain excellent results in real problems of very short-term wind speed prediction, improving ...
This paper evaluates the performance of different types of Regression Trees (RTs) in a real problem of very short-term wind speed prediction from measuring data in wind farms. ...
Acknowledgments The authors would like to thank Spanish Ministry of Science and Technology, Junta de Andalucía and Pablo de Olavide University for the support under projects ECO2010-22065-C03-02 and TIN2011 ...
doi:10.1016/j.renene.2015.03.071
fatcat:fedioghxyfb6jpyatramarntoi
Principles and Algorithms for Forecasting Groups of Time Series: Locality and Globality
[article]
2021
arXiv
pre-print
Formalizing the setting of forecasting a set of time series with local and global methods, we provide the following contributions: 1) Global methods are not more restrictive than local methods, both can ...
Global models can succeed in a wider range of problems than previously thought. 2) Basic generalization bounds for local and global algorithms. ...
to keep up. ...
arXiv:2008.00444v3
fatcat:ggy5gp3xc5hsnidonx5mbkzvqq
An Internal Clock Based Space-time Neural Network for Motion Speed Recognition
[article]
2020
arXiv
pre-print
Therefore, our system takes unique learning advantages of the requirement of the small dataset, quick learning and low power performance, which shows great potentials for edge or scalable AI-based applications ...
The inference accuracy can be up to 83.3% (cartoon videos) and 75% (real-world videos). Meanwhile, the system only requires six video datasets in the learning stage and with up to 42 training trials. ...
of motions with subtle speed gap such as slow run and fast walk; 3) recognition of real-world motion videos based on knowledge learned from cartoon videos. ...
arXiv:2001.10159v1
fatcat:r5usbn6hwjbmdjplh27xf3izcu
Exploiting Code Redundancies in ECOC
[chapter]
2010
Lecture Notes in Computer Science
We study an approach for speeding up the training of error-correcting output codes (ECOC) classifiers. ...
on adapted caching and weight reuse, which guarantees that the learned model is the same as per batch learning. ...
Cache Strategy It is well-known that caching of kernel evaluations provides significant speed-up for the learning with SVMs [10] . ...
doi:10.1007/978-3-642-16184-1_19
fatcat:6jftbn2jqzgfhj6lsudelxlyy4
Weight Divergence Driven Divide-and-Conquer Approach for Optimal Federated Learning from non-IID Data
[article]
2021
arXiv
pre-print
Addressing the ability to handle data heterogeneity (non-identical and independent distribution or non-IID) is a key enabler for the wider deployment of Federated Learning. ...
We propose a novel use of Cosine-distance based Weight Divergence metric to determine the exact point where a Deep Learning network can be divided into class agnostic initial layers and class-specific ...
In Federated Learning, a central server shares a global model with participating client devices and the model is trained on the local datasets available at the client device. ...
arXiv:2106.14503v2
fatcat:hnzd2oy6jzbz7mh73c6tltooka
Bogie Stability Control and Management Using Data Driven Analysis Techniques for High-Speed Trains
2022
Applied Sciences
factors, and set up rules for BIDS alarms. ...
Taking the Taiwan High Speed Rail Corporation (THSRC) as an example, there have been ongoing reports of BIDS alarms since its launch. ...
Conflicts of Interest: The authors declare no conflict of interest. Appl. Sci. 2022, 12, 2389 ...
doi:10.3390/app12052389
fatcat:5fwcbg2bsbepfemhdmn4yteste
Orbit: Probabilistic Forecast with Exponential Smoothing
[article]
2021
arXiv
pre-print
Our model refinements include additional global trend, transformation for multiplicative form, noise distribution and choice of priors. ...
Although we see an increasing amount of adoptions of machine learning methods in solving some of those forecasting challenges, statistical methods remain powerful while dealing with low granularity data ...
level, local trend, global trend, seasonality and error term, respectively. ...
arXiv:2004.08492v4
fatcat:ui3bmiafsvffbmvf5vzdnrxigm
A knowledge-based code generator generator
1977
Proceedings of the 1977 symposium on Artificial intelligence and programming languages -
XGEN is a program that accepts a machine description and produces a good local code generator for an ALGOL-like language. ...
It is organized as a production system of rules codifying previously acquired human skills for dealing with computer architecture and programming ~anguages. ...
Ignoring them, however, is ignoring the experience that "the quality of the local code has a greater impact on both the size and speed of the final program than any other optimization" I15]. ...
doi:10.1145/800228.806941
fatcat:2nox32i7sfc7tjq7gxtejio2ke
A knowledge-based code generator generator
1977
ACM SIGART Bulletin
XGEN is a program that accepts a machine description and produces a good local code generator for an ALGOL-like language. ...
It is organized as a production system of rules codifying previously acquired human skills for dealing with computer architecture and programming ~anguages. ...
Ignoring them, however, is ignoring the experience that "the quality of the local code has a greater impact on both the size and speed of the final program than any other optimization" I15]. ...
doi:10.1145/872736.806941
fatcat:fhdh2bvjwndxjf43vnyn5j6ucu
A knowledge-based code generator generator
1977
SIGPLAN notices
XGEN is a program that accepts a machine description and produces a good local code generator for an ALGOL-like language. ...
It is organized as a production system of rules codifying previously acquired human skills for dealing with computer architecture and programming ~anguages. ...
Ignoring them, however, is ignoring the experience that "the quality of the local code has a greater impact on both the size and speed of the final program than any other optimization" I15]. ...
doi:10.1145/872734.806941
fatcat:5452bp6cdjhh5ikwinl74n666u
HERMES: Hybrid Error-corrector Model with inclusion of External Signals for nonstationary fashion time series
[article]
2023
arXiv
pre-print
This hybrid model provides state-of-the-art results on the proposed fashion dataset, on the weekly time series of the M4 competition, and illustrates the benefit of the contribution of external weak signals ...
Our approach combines per-time-series parametric models with seasonal components and a global recurrent neural network to include sporadic external signals. ...
It allows the use of GPU to speed up the training process.
Benchmarks, hybrid models and Metrics As benchmarks, several widespread statistical methods and deep learning approaches were selected. ...
arXiv:2202.03224v3
fatcat:srzqx7dbsfemlhst2kisbjvya4
Page 560 of Astronomy and Astrophysics Vol. 300, Issue 2
[page]
1995
Astronomy and Astrophysics
Up to now, most of the attention (both theoretical and observational) has been focused on the relativistic contributions to the (lunar) translational motion and local frame definitions +. ...
Suc- cess of DSX is based on precise distinguishing between global (barycentric) translational motion of the bodies and their local rotational motion resulting in careful usage of corresponding global ...
« Previous
Showing results 1 — 15 out of 4,058 results