The Experts below are selected from a list of 712413 Experts worldwide ranked by ideXlab platform
J F Meyer - One of the best experts on this subject based on the ideXlab platform.
-
reduced Base Model construction methods for stochastic activity networks
IEEE Journal on Selected Areas in Communications, 1991Co-Authors: William H Sanders, J F MeyerAbstract:Reduced Base Model construction methods for stochastic activity networks are discussed. The basic definitions concerning stochastic networks are reviewed and the types of variables used in the construction process are defined. These variables can be used to estimate both transient and steady-state system characteristics. The construction operations used and theorems stating the validity of the method are presented. A procedure for generating the reduced Base Model stochastic process for a given stochastic activity network and performance variable is presented. Some examples which illustrate the method and demonstrate its effectiveness in reducing the size of a state space are presented. >
Karthikeyan Shanmugam - One of the best experts on this subject based on the ideXlab platform.
-
confidence scoring using whitebox meta Models with linear classifier probes
International Conference on Artificial Intelligence and Statistics, 2019Co-Authors: Tongfei Chen, Jiri Navratil, Vijay S Iyengar, Karthikeyan ShanmugamAbstract:We propose a novel confidence scoring mechanism for deep neural networks Based on a two-Model paradigm involving a Base Model and a meta-Model. The confidence score is learned by the meta-Model observing the Base Model succeeding/failing at its task. As features to the meta-Model, we investigate linear classifier probes inserted between the various layers of the Base Model. Our experiments demonstrate that this approach outperforms multiple Baselines in a filtering task, i.e., task of rejecting samples with low confidence. Experimental results are presented using CIFAR-10 and CIFAR-100 dataset with and without added noise. We discuss the importance of confidence scoring to bridge the gap between experimental and real-world applications.
-
confidence scoring using whitebox meta Models with linear classifier probes
arXiv: Learning, 2018Co-Authors: Tongfei Chen, Jiri Navratil, Vijay S Iyengar, Karthikeyan ShanmugamAbstract:We propose a novel confidence scoring mechanism for deep neural networks Based on a two-Model paradigm involving a Base Model and a meta-Model. The confidence score is learned by the meta-Model observing the Base Model succeeding/failing at its task. As features to the meta-Model, we investigate linear classifier probes inserted between the various layers of the Base Model. Our experiments demonstrate that this approach outperforms various Baselines in a filtering task, i.e., task of rejecting samples with low confidence. Experimental results are presented using CIFAR-10 and CIFAR-100 dataset with and without added noise. We discuss the importance of confidence scoring to bridge the gap between experimental and real-world applications.
William H Sanders - One of the best experts on this subject based on the ideXlab platform.
-
reduced Base Model construction methods for stochastic activity networks
IEEE Journal on Selected Areas in Communications, 1991Co-Authors: William H Sanders, J F MeyerAbstract:Reduced Base Model construction methods for stochastic activity networks are discussed. The basic definitions concerning stochastic networks are reviewed and the types of variables used in the construction process are defined. These variables can be used to estimate both transient and steady-state system characteristics. The construction operations used and theorems stating the validity of the method are presented. A procedure for generating the reduced Base Model stochastic process for a given stochastic activity network and performance variable is presented. Some examples which illustrate the method and demonstrate its effectiveness in reducing the size of a state space are presented. >
Tongfei Chen - One of the best experts on this subject based on the ideXlab platform.
-
confidence scoring using whitebox meta Models with linear classifier probes
International Conference on Artificial Intelligence and Statistics, 2019Co-Authors: Tongfei Chen, Jiri Navratil, Vijay S Iyengar, Karthikeyan ShanmugamAbstract:We propose a novel confidence scoring mechanism for deep neural networks Based on a two-Model paradigm involving a Base Model and a meta-Model. The confidence score is learned by the meta-Model observing the Base Model succeeding/failing at its task. As features to the meta-Model, we investigate linear classifier probes inserted between the various layers of the Base Model. Our experiments demonstrate that this approach outperforms multiple Baselines in a filtering task, i.e., task of rejecting samples with low confidence. Experimental results are presented using CIFAR-10 and CIFAR-100 dataset with and without added noise. We discuss the importance of confidence scoring to bridge the gap between experimental and real-world applications.
-
confidence scoring using whitebox meta Models with linear classifier probes
arXiv: Learning, 2018Co-Authors: Tongfei Chen, Jiri Navratil, Vijay S Iyengar, Karthikeyan ShanmugamAbstract:We propose a novel confidence scoring mechanism for deep neural networks Based on a two-Model paradigm involving a Base Model and a meta-Model. The confidence score is learned by the meta-Model observing the Base Model succeeding/failing at its task. As features to the meta-Model, we investigate linear classifier probes inserted between the various layers of the Base Model. Our experiments demonstrate that this approach outperforms various Baselines in a filtering task, i.e., task of rejecting samples with low confidence. Experimental results are presented using CIFAR-10 and CIFAR-100 dataset with and without added noise. We discuss the importance of confidence scoring to bridge the gap between experimental and real-world applications.
Daniel M Prevedello - One of the best experts on this subject based on the ideXlab platform.
-
Endoscopic endonasal cranial Base surgery simulation using an artificial cranial Base Model created by selective laser sintering
Neurosurgical Review, 2015Co-Authors: Kenichi Oyama, Leo F. S. Ditzel Filho, Daniel G. Souza, Bradley A Otto, Ricardo L Carrau, Jun Muto, Ramazan Gun, Daniel M PrevedelloAbstract:Mastery of the expanded endoscopic endonasal approach (EEA) requires anatomical knowledge and surgical skills; the learning curve for this technique is steep. To a great degree, these skills can be gained by cadaveric dissections; however, ethical, religious, and legal considerations may interfere with this paradigm in different regions of the world. We assessed an artificial cranial Base Model for the surgical simulation of EEA and compared its usefulness with that of cadaveric specimens. The Model is made of both polyamide nylon and glass beads using a selective laser sintering (SLS) technique to reflect CT-DICOM data of the patient’s head. It features several artificial cranial Base structures such as the dura mater, venous sinuses, cavernous sinuses, internal carotid arteries, and cranial nerves. Under endoscopic view, the Model was dissected through the nostrils using a high-speed drill and other endonasal surgical instruments. Anatomical structures around and inside the sphenoid sinus were accurately reconstructed in the Model, and several important surgical landmarks, including the medial and lateral optico-carotid recesses and vidian canals, were observed. The bone was removed with a high-speed drill until it was eggshell thin and the dura mater was preserved, a technique very similar to that applied in patients during endonasal cranial Base approaches. The Model allowed simulation of almost all sagittal and coronal plane EEA modules. SLS Modeling is a useful tool for acquiring the anatomical knowledge and surgical expertise for performing EEA while avoiding the ethical, religious, and infection-related problems inherent with use of cadaveric specimens.