Results 271 to 280 of about 294,503 (315)
Some of the next articles are maybe not open access.
Optimal adaptive estimation: Structure and parameter adaptation
1970 IEEE Symposium on Adaptive Processes (9th) Decision and Control, 1970Optimal structure and parameter adaptive estimators have been obtained for continuous as well as discrete data gaussian process models with linear dynamics. Specifically, the essentially nonlinear adaptive estimators are shown to be decomposable (partition theorem) into two parts, a linear non-adaptive part consisting of a bank of Kalman-Bucy filters ...
openaire +1 more source
IEEE Transactions on Circuits and Systems for Video Technology, 2017
In many real-world applications, labeled data are either expensive or too scarce to be used to train an accurate classifier. Therefore, it is worth exploring and often essential to make full use of existing resources. Domain adaptation is one of the most promising techniques of leveraging an existing well-labeled source domain and a limited labeled ...
Jingjing Li, Yue Wu, Ke Lu
openaire +1 more source
In many real-world applications, labeled data are either expensive or too scarce to be used to train an accurate classifier. Therefore, it is worth exploring and often essential to make full use of existing resources. Domain adaptation is one of the most promising techniques of leveraging an existing well-labeled source domain and a limited labeled ...
Jingjing Li, Yue Wu, Ke Lu
openaire +1 more source
Adaptive hierarchical structures
1995The construction of a hierarchical system to distinguish classes of patterns can be improved by the combination of a dynamical elastic matching with a time dependent image resolution. Using the elastic matching as a preprocessing for synergetic computers one achieves an invariant perception by means of arbitrary spatial transformations.
A. Daffertshofer, H. Haken
openaire +1 more source
2016
Novel programming paradigms enable the concurrent execution and the dynamic run-time rescheduling of several competing applications on large heterogeneous multi-core systems. However, today the cache memory is still statically allocated at design time. This leads to a distribution of memory resources that is optimized for an average use case.
Tradowsky, Carsten +4 more
openaire +2 more sources
Novel programming paradigms enable the concurrent execution and the dynamic run-time rescheduling of several competing applications on large heterogeneous multi-core systems. However, today the cache memory is still statically allocated at design time. This leads to a distribution of memory resources that is optimized for an average use case.
Tradowsky, Carsten +4 more
openaire +2 more sources
Domain Adaptation for Structured Regression
International Journal of Computer Vision, 2013zbMATH Open Web Interface contents unavailable due to conflicting licenses.
Yamada, Makoto, Sigal, Leonid, Chang, Yi
openaire +2 more sources
Complex adaptation and system structure
Biosystems, 2007The structural organization of biological systems is one of nature's most fascinating aspects, but its origin and functional role is not yet fully understood. For instance, basic adaptational mechanisms like genetic mutation and Hebbian adaptation seem to be generic and invariant across many species and are, on their own, fairly well investigated and ...
Marc, Toussaint, Werner, von Seelen
openaire +2 more sources
1988., IEEE International Symposium on Circuits and Systems, 2003
The concept of structural adaptivity is analyzed and the problems and methods of implementation are discussed. It is shown that the application of dynamic, graph computation models and various artificial-intelligence programming techniques, particularly declarative programming, can lead to the practical implementation of this novel system category. >
openaire +1 more source
The concept of structural adaptivity is analyzed and the problems and methods of implementation are discussed. It is shown that the application of dynamic, graph computation models and various artificial-intelligence programming techniques, particularly declarative programming, can lead to the practical implementation of this novel system category. >
openaire +1 more source
Structure adaptation of linear MMSE adaptive filters
IEE Proceedings - Vision, Image, and Signal Processing, 2004The tap-length, or the number of the taps, is an important structural parameter of the linear MMSE adaptive filter. Although the optimum tap-length that balances performance and complexity varies with scenarios, most current adaptive filters fix the tap-length at some compromise value, making them inefficient to implement especially in time-varying ...
Y. Gong, C.F.N. Cowan
openaire +1 more source
Adaptive structures with algebraic loops
IEEE Transactions on Neural Networks, 2001The contraction theorem has many fields of application, including linear algebraic equations, differential and integral equations, control systems theory, optimization, etc. The paper aims at showing how contraction mapping can be applied to the computation and the training of adaptive structures with algebraic loops.
openaire +2 more sources