| Towards Robust Waveform-Based Acoustic Models | 0 | 0.34 | 2022 |
| Learning Waveform-Based Acoustic Models Using Deep Variational Convolutional Neural Networks | 0 | 0.34 | 2021 |
| Memory functions reveal structural properties of gene regulatory networks. | 0 | 0.34 | 2018 |
| Phase Diagram of Restricted Boltzmann Machines and Generalised Hopfield Networks with Arbitrary Priors. | 4 | 0.42 | 2018 |
| Dynamical selection of Nash equilibria using Experience Weighted Attraction Learning: emergence of heterogeneous mixed equilibria. | 0 | 0.34 | 2017 |
| Phase transitions in Restricted Boltzmann Machines with generic priors. | 0 | 0.34 | 2016 |
| A Subband-Based SVM Front-End for Robust ASR. | 0 | 0.34 | 2014 |
| Effects of domain-specific SVM kernel design on the robustness of automatic speech recognition | 0 | 0.34 | 2013 |
| Random walk kernels and learning curves for Gaussian process regression on random graphs | 2 | 0.37 | 2013 |
| Phoneme Classification in High-Dimensional Linear Feature Domains. | 1 | 0.36 | 2013 |
| Learning curves for multi-task Gaussian process regression. | 0 | 0.34 | 2012 |
| Learning curves for multi-task Gaussian process regression | 0 | 0.34 | 2012 |
| Combined waveform-cepstral representation for robust speech recognition | 0 | 0.34 | 2011 |
| Exact learning curves for Gaussian process regression on large random graphs. | 1 | 0.35 | 2010 |
| Subband acoustic waveform front-end for robust speech recognition using support vector machines | 1 | 0.37 | 2010 |
| Tuning Support Vector Machines For Robust Phoneme Classification With Acoustic Waveforms | 4 | 0.44 | 2009 |
| Kernels and learning curves for Gaussian process regression on random graphs. | 2 | 0.37 | 2009 |
| Custom-designed SVM kernels for improved robustness of phoneme classification | 3 | 0.40 | 2009 |
| Robust phoneme classification: Exploiting the adaptability of acoustic waveform models | 2 | 0.38 | 2009 |
| Towards robust phoneme classification: Augmentation of PLP models with acoustic waveforms | 3 | 0.45 | 2008 |
| Combined PLP - Acoustic waveform classification for robust phoneme recognition using support vector machines | 1 | 0.36 | 2008 |
| ROBUSTNESS OF PHONEME CLASSIFICATION IN DIFFERENT REPRESENTATION SPACES | 0 | 0.34 | 2006 |
| Bayesian approach to feature selection and parameter tuning for support vector machine classifiers. | 28 | 1.59 | 2005 |
| Understanding gaussian process regression using the equivalent kernel | 13 | 0.81 | 2004 |
| Using the Equivalent Kernel to Understand Gaussian Process Regression | 10 | 0.68 | 2004 |
| Can gaussian process regression be made robust against model mismatch? | 1 | 0.36 | 2004 |
| Model selection for support vector machine classification | 45 | 2.80 | 2003 |
| Bayesian Methods for Support Vector Machines: Evidence and Predictive Class Probabilities | 60 | 5.04 | 2002 |
| Learning Curves for Gaussian Process Regression: Approximations and Bounds | 17 | 1.11 | 2002 |
| Gaussian Process Regression with Mismatched Models | 5 | 0.44 | 2001 |
| On-line learning with restricted training sets: exact solution as benchmark for general theories | 0 | 0.34 | 1998 |
| Online learning from finite training sets and robustness to input bias. | 5 | 0.80 | 1998 |
| Learning curves for Gaussian processes | 11 | 1.98 | 1998 |
| Online learning from finite training sets in nonlinear networks | 0 | 0.34 | 1997 |
| Minimum entropy queries for linear students learning nonlinear rules. | 2 | 0.52 | 1995 |
| Learning With Ensembles: How Over-Fitting Can Be Useful | 69 | 10.82 | 1995 |
| Test error fluctuations in finite linear perceptrons | 2 | 1.26 | 1995 |
| Learning from queries for maximum information gain in imperfectly learnable problems | 5 | 0.82 | 1994 |
| Learning in large linear perceptrons and why the thermodynamic limit is relevant to the real world | 1 | 0.39 | 1994 |
