Microsoft Research Cambridge
Author pages are created from data sourced from our academic publisher partnerships and public sources.
Share This Author
Real-valued (Medical) Time Series Generation with Recurrent Conditional GANs
This work proposes a Recurrent GAN (RGAN) and Recurrent Conditional GGAN (RCGAN) to produce realistic real-valued multi-dimensional time series, with an emphasis on their application to medical data.
Identification of active transcriptional regulatory elements with GRO-seq
dREG is introduced, a sensitive machine learning method that uses support vector regression to identify active TREs from GRO-seq data without requiring cap-based enrichment, and predicted TREs are more enriched for several marks of transcriptional activation than those identified by alternative functional assays.
Neural Document Embeddings for Intensive Care Patient Mortality Prediction
- Paulina Grnarova, Florian Schmidt, Stephanie L. Hyland, Carsten Eickhoff
- Computer ScienceNIPS
- 1 December 2016
A convolutional document embedding approach based on the unstructured textual content of clinical notes shows significant performance gains compared to previously employed methods such as latent topic distributions or generic doc2vec embeddings for post-discharge mortality prediction.
Learning Unitary Operators with Help From u(n)
This work describes a parametrization using the Lie algebra u(n) associated with the Lie group U( n) of n × n unitary matrices that is closed under additive updates of these coefficients, and provides a simple space in which to do gradient descent.
Improving Clinical Predictions through Unsupervised Time Series Representation Learning
- Xinrui Lyu, Matthias Hüser, Stephanie L. Hyland, George Zerveas, G. Rätsch
- Computer ScienceArXiv
- 2 December 2018
This work experiments with using sequence-to-sequence (Seq2Seq) models in two different ways, as an autoencoder and as a forecaster, and shows that the best performance is achieved by a forecasting Seq2 Seq model with an integrated attention mechanism.
Early prediction of circulatory failure in the intensive care unit using machine learning
An early-warning system that integrates measurements from multiple organ systems using a high-resolution database with 240 patient-years of data that predicts 90% of circulatory-failure events and provides early identification of patients at risk for circulatory failure with a much lower false-alarm rate than conventional threshold-based systems.
A global metagenomic map of urban microbiomes and antimicrobial resistance
Machine Learning for Health (ML4H) 2020: Advancing Healthcare for All
The sixth Machine Learning for Health (ML4H) workshop1 was held virtually on December 11, 2020, in conjunction with the Thirty-fourth Conference on Neural Information Processing Systems (NeurIPS…
On the Intrinsic Privacy of Stochastic Gradient Descent
This work takes the first step towards analysing the intrinsic privacy properties of stochastic gradient descent (SGD), and proposes a method to augment the intrinsic noise of SGD to achieve the desired $\epsilon$.
A Generative Model of Words and Relationships from Multiple Sources
A generative model is proposed which integrates evidence from diverse data sources, enabling the sharing of semantic information by generalising the concept of co-occurrence from distributional semantics to include other relationships between entities or words, which are model as affine transformations on the embedding space.