The Experts below are selected from a list of 47151 Experts worldwide ranked by ideXlab platform

Hynek Hermansky - One of the best experts on this subject based on the ideXlab platform.

  • Sparse Multilayer Perceptron for phoneme recognition
    IEEE Transactions on Audio Speech and Language Processing, 2012
    Co-Authors: Garimella S. V. S. Sivaram, Hynek Hermansky
    Abstract:

    This paper introduces the sparse Multilayer Perceptron (SMLP) which jointly learns a sparse feature representation and nonlinear classifier boundaries to optimally discriminate multiple output classes. SMLP learns the transformation from the inputs to the targets as in Multilayer Perceptron (MLP) while the outputs of one of the internal hidden layers is forced to be sparse. This is achieved by adding a sparse regularization term to the cross-entropy cost and updating the parameters of the network to minimize the joint cost. On the TIMIT phoneme recognition task, SMLP-based systems trained on individual speech recognition feature streams perform significantly better than the corresponding MLP-based systems. Phoneme error rate of 19.6% is achieved using the combination of SMLP-based systems, a relative improvement of 3.0% over the combination of MLP-based systems.

  • Multilayer Perceptron with sparse hidden outputs for phoneme recognition
    International Conference on Acoustics Speech and Signal Processing, 2011
    Co-Authors: Garimella S. V. S. Sivaram, Hynek Hermansky
    Abstract:

    This paper introduces the sparse Multilayer Perceptron (SMLP) which learns the transformation from the inputs to the targets as in Multilayer Perceptron (MLP) while the outputs of one of the internal hidden layers is forced to be sparse. This is achieved by adding a sparse regularization term to the cross-entropy cost and learning the parameters of the network to minimize the joint cost. On the TIMIT phoneme recognition task, the SMLP based system trained using perceptual linear prediction (PLP) features performs better than the conventional MLP based system. Furthermore, their combination yields a phoneme error rate of 21.2%, a relative improvement of 6.2% over the baseline.

Garimella S. V. S. Sivaram - One of the best experts on this subject based on the ideXlab platform.

  • Sparse Multilayer Perceptron for phoneme recognition
    IEEE Transactions on Audio Speech and Language Processing, 2012
    Co-Authors: Garimella S. V. S. Sivaram, Hynek Hermansky
    Abstract:

    This paper introduces the sparse Multilayer Perceptron (SMLP) which jointly learns a sparse feature representation and nonlinear classifier boundaries to optimally discriminate multiple output classes. SMLP learns the transformation from the inputs to the targets as in Multilayer Perceptron (MLP) while the outputs of one of the internal hidden layers is forced to be sparse. This is achieved by adding a sparse regularization term to the cross-entropy cost and updating the parameters of the network to minimize the joint cost. On the TIMIT phoneme recognition task, SMLP-based systems trained on individual speech recognition feature streams perform significantly better than the corresponding MLP-based systems. Phoneme error rate of 19.6% is achieved using the combination of SMLP-based systems, a relative improvement of 3.0% over the combination of MLP-based systems.

  • Multilayer Perceptron with sparse hidden outputs for phoneme recognition
    International Conference on Acoustics Speech and Signal Processing, 2011
    Co-Authors: Garimella S. V. S. Sivaram, Hynek Hermansky
    Abstract:

    This paper introduces the sparse Multilayer Perceptron (SMLP) which learns the transformation from the inputs to the targets as in Multilayer Perceptron (MLP) while the outputs of one of the internal hidden layers is forced to be sparse. This is achieved by adding a sparse regularization term to the cross-entropy cost and learning the parameters of the network to minimize the joint cost. On the TIMIT phoneme recognition task, the SMLP based system trained using perceptual linear prediction (PLP) features performs better than the conventional MLP based system. Furthermore, their combination yields a phoneme error rate of 21.2%, a relative improvement of 6.2% over the baseline.

Dani Agung Prastiyo - One of the best experts on this subject based on the ideXlab platform.

  • Deteksi Lateral Movement Berdasarkan Malicious Command Dan Control Menggunakan Multilayer Perceptron
    2019
    Co-Authors: Dani Agung Prastiyo, Parman Sukarno, Erwid Musthofa Jadied
    Abstract:

    Abstrak PenelitianinimembangunmodelpendeteksianseranganlateralmovementpadainfrastrukturwindowsdenganmenggunakanmodelMultilayerPerceptron(MLP)sebagaivalidasicommanddancontrolberbahaya. Salah satu jenis serangan paling berbahaya pada Windows adalah advanced persistant threat fase lateral movementkarenapadaakhirnyadapatmemberikanakseskeactivedirectorydanmemberikankontrolpenuhatasinfrastrukturberbasisWindows. Sejumlahpenelitiantelahdilakukanuntukmendeteksiserangan ini. Namun, keakuratandeteksimasihperluditingkatkan. Untukmeningkatkanakurasi, MLPdigunakan dimana salah satu propertinya cocok untuk menangani data non-linear separable seperti yang ditemukan dalamdatasetJPCERT/CC.AkurasideteksiyangdicapaiuntukmodelMultilayerPerceptronadalah97,26 %. Hasilinimengunggulimetodelainyangada. Katakunci: lateralmovement,advancedpersistantthreat,windows,commandandcontrol,mlp Abstract This research builds a model detection of lateral movement attacks on Windows machine by using a Multilayer Perceptron (MLP) model as a validation of malicious command and control detection. One of the most dangerous types of attacks on Windows is the advanced persistent threat phase lateral movement as thistypeofattackcanultimatelyprovideaccesstoactivedirectoryandprovidefullcontroloverWindowsbasedinfrastructure. Anumberofresearchhasbeenconductedtodetectthisattack. However,theaccuracy of the detection is still need to be improved. In order to enhance the accuracy, the MLP is used where one of its properties is suitable to deal with non-linear separable data as found in JPCERT/CC dataset. The achieved detection accuracy for the Multilayer Perceptron model is 97.26%. This result outperforms any otherexistingmethods. Keywords: lateralmovement,advancedpersistantthreat,windows,commandandcontrol,mlp

  • Deteksi Lateral Movement Berdasarkan Malicious Command dan Control Menggunakan Multilayer Perceptron
    Universitas Telkom, 2019
    Co-Authors: Dani Agung Prastiyo
    Abstract:

    Penelitian ini membangun model pendeteksian serangan lateral movement pada infrastruktur windows dengan menggunakan model Multilayer Perceptron (MLP) sebagai validasi command dan control berbahaya. Salah satu jenis serangan paling berbahaya pada Windows adalah advanced persistant threat fase lateral movement karena pada akhirnya dapat memberikan akses ke active directory dan memberikan kontrol penuh atas infrastruktur berbasis Windows. Sejumlah penelitian telah dilakukan untuk mendeteksi serangan ini. Namun, keakuratan deteksi masih perlu ditingkatkan. Untuk meningkatkan akurasi, MLP digunakan dimana salah satu propertinya cocok untuk menangani data non-linear separable seperti yang ditemukan dalam dataset JPCERT/CC. Akurasi deteksi yang dicapai untuk model Multilayer Perceptron adalah 97,26 %. Hasil ini mengungguli metode lain yang ad

Michael T. Manry - One of the best experts on this subject based on the ideXlab platform.

  • Conventional modeling of the Multilayer Perceptron using polynomial basis functions
    IEEE Transactions on Neural Networks, 1993
    Co-Authors: Mu-song Chen, Michael T. Manry
    Abstract:

    A technique for modeling the Multilayer Perceptron (MLP) neural network, in which input and hidden units are represented by polynomial basis functions (PBFs), is presented. The MLP output is expressed as a linear combination of the PBFs and can therefore be expressed as a polynomial function of its inputs. Thus, the MLP is isomorphic to conventional polynomial discriminant classifiers or Volterra filters. The modeling technique was successfully applied to several trained MLP networks. >

  • Enhanced robustness of Multilayer Perceptron training
    Conference Record of the Thirty-Sixth Asilomar Conference on Signals Systems and Computers 2002., 1
    Co-Authors: Walter H. Delashmit, Michael T. Manry
    Abstract:

    Due to the chaotic nature of Multilayer Perceptron training, training error usually fails to be a monotonically non-increasing function of the number of hidden units. An initialization and training methodology is developed to significantly increase the probability that the training error is monotonically non-increasing. First a structured initialization generates the random weights in a particular order. Second, larger networks are initialized using weights from smaller trained networks. Lastly, the required number of iterations is calculated as a function of network size.

B. De Moor - One of the best experts on this subject based on the ideXlab platform.

  • Lur'e systems with Multilayer Perceptron and recurrent neural networks: absolute stability and dissipativity
    IEEE Transactions on Automatic Control, 1999
    Co-Authors: J.a.k. Soykens, J. Vandewalle, B. De Moor
    Abstract:

    Sufficient conditions for absolute stability and dissipativity of continuous-time recurrent neural networks with two hidden layers are presented. In the autonomous case this is related to a Lur'e system with Multilayer Perceptron nonlinearity. Such models are obtained after parametrizing general nonlinear models and controllers by a Multilayer Perceptron with one hidden layer and representing the control scheme in standard plant form. The conditions are expressed as matrix inequalities and can be employed for nonlinear H/sub /spl infin// control and imposing closed-loop stability in dynamic backpropagation.