User profiles for George E. Dahl
George E. DahlGoogle Inc. Verified email at google.com Cited by 50547 |
Deep neural networks for acoustic modeling in speech recognition: The shared views of four research groups
Most current speech recognition systems use hidden Markov models (HMMs) to deal with the
temporal variability of speech and Gaussian mixture models (GMMs) to determine how well …
temporal variability of speech and Gaussian mixture models (GMMs) to determine how well …
Neural message passing for quantum chemistry
Supervised learning on molecules has incredible potential to be useful in chemistry, drug
discovery, and materials science. Luckily, several promising and closely related neural …
discovery, and materials science. Luckily, several promising and closely related neural …
Context-dependent pre-trained deep neural networks for large-vocabulary speech recognition
We propose a novel context-dependent (CD) model for large-vocabulary speech recognition
(LVSR) that leverages recent advances in using deep belief networks for phone recognition…
(LVSR) that leverages recent advances in using deep belief networks for phone recognition…
Acoustic modeling using deep belief networks
Gaussian mixture models are currently the dominant technique for modeling the emission
distribution of hidden Markov models for speech recognition. We show that better phone …
distribution of hidden Markov models for speech recognition. We show that better phone …
Improving deep neural networks for LVCSR using rectified linear units and dropout
Recently, pre-trained deep neural networks (DNNs) have outperformed traditional acoustic
models based on Gaussian mixture models (GMMs) on a variety of large vocabulary speech …
models based on Gaussian mixture models (GMMs) on a variety of large vocabulary speech …
Deep neural nets as a method for quantitative structure–activity relationships
Neural networks were widely used for quantitative structure–activity relationships (QSAR) in
the 1990s. Because of various practical issues (eg, slow on large problems, difficult to train, …
the 1990s. Because of various practical issues (eg, slow on large problems, difficult to train, …
Detecting cancer metastases on gigapixel pathology images
Each year, the treatment decisions for more than 230,000 breast cancer patients in the US
hinge on whether the cancer has metastasized away from the breast. Metastasis detection is …
hinge on whether the cancer has metastasized away from the breast. Metastasis detection is …
Large-scale malware classification using random projections and neural networks
Automatically generated malware is a significant problem for computer users. Analysts are
able to manually investigate a small number of unknown files, but the best large-scale …
able to manually investigate a small number of unknown files, but the best large-scale …
Prediction errors of molecular machine learning models lower than hybrid DFT error
We investigate the impact of choosing regressors and molecular representations for the
construction of fast machine learning (ML) models of 13 electronic ground-state properties of …
construction of fast machine learning (ML) models of 13 electronic ground-state properties of …
Large scale distributed neural network training through online distillation
Techniques such as ensembling and distillation promise model quality improvements when
paired with almost any base model. However, due to increased test-time cost (for ensembles…
paired with almost any base model. However, due to increased test-time cost (for ensembles…