d909b
Director for Machine Learning and Artificial Intelligence at GSK. Previously: ML at Roche, PhD in ML for Healthcare, ETH Zurich
GSKZurich, Switzerland
Pinned Repositories
ame
🤖🤖 Attentive Mixtures of Experts (AMEs) are neural network models that learn to output both accurate predictions and estimates of feature importance for individual samples.
CGE-Piano
A piano scene for the computer graphics class project, using OpenGL, OpenAL, assimp and GLFW.
CovEWS
The COVID-19 Early Warning System (CovEWS) is a real-time early warning system for assessing individual COVID-19 related mortality risk.
cxplain
Causal Explanation (CXPlain) is a method for explaining the predictions of any machine-learning model.
drnet
💉📈 Dose response networks (DRNets) are a method for learning to estimate individual dose-response curves for multiple parametric treatments from observational data using neural networks.
DSMT-Nets
👓📡 Distantly Supervised Multitask Networks (DSMT-Nets) are a deep-learning approach to semi-supervised learning that utilises distant supervision through many auxiliary tasks.
eth_dream_pd_subchallenge1
🚶📱 A deep-learning approach to automatically extract digital biomarkers for Parkinson's disease from smartphone accelerometers.
heart_rhythm_attentive_rnn
❤️📱 Heart rhythm classification from mobile event recorder data using attentive neural networks.
ncore
perfect_match
➕➕ Perfect Match is a simple method for learning representations for counterfactual inference with neural networks.
d909b's Repositories
d909b/cxplain
Causal Explanation (CXPlain) is a method for explaining the predictions of any machine-learning model.
d909b/perfect_match
➕➕ Perfect Match is a simple method for learning representations for counterfactual inference with neural networks.
d909b/drnet
💉📈 Dose response networks (DRNets) are a method for learning to estimate individual dose-response curves for multiple parametric treatments from observational data using neural networks.
d909b/ame
🤖🤖 Attentive Mixtures of Experts (AMEs) are neural network models that learn to output both accurate predictions and estimates of feature importance for individual samples.
d909b/CovEWS
The COVID-19 Early Warning System (CovEWS) is a real-time early warning system for assessing individual COVID-19 related mortality risk.
d909b/DSMT-Nets
👓📡 Distantly Supervised Multitask Networks (DSMT-Nets) are a deep-learning approach to semi-supervised learning that utilises distant supervision through many auxiliary tasks.
d909b/heart_rhythm_attentive_rnn
❤️📱 Heart rhythm classification from mobile event recorder data using attentive neural networks.
d909b/eth_dream_pd_subchallenge1
🚶📱 A deep-learning approach to automatically extract digital biomarkers for Parkinson's disease from smartphone accelerometers.
d909b/ncore
d909b/CGE-Piano
A piano scene for the computer graphics class project, using OpenGL, OpenAL, assimp and GLFW.
d909b/SWPUE1-Singleton
A simple singleton pattern demonstration
d909b/SWPUE11-ChainOfResponsibility
A simple Chain Of Responsibility pattern demonstration.
d909b/SWPUE3-Plugin
A simple plugin pattern demonstration.
d909b/SWPUE4-Composite
A simple composite pattern demonstration
d909b/SWPUE5-Observer
A simple observer pattern demonstration.
d909b/SWPUE7-Adapter
A simple adapter pattern demonstration.
d909b/CPP-OOP-Exercises
The exercises for OOP in CPP class.
d909b/d909b.github.io
My personal website built with Angular and Jekyll.
d909b/extd_med_benchmark
d909b/GADEL-Snake
A snake clone for GADEL class using the Angle engine.
d909b/SKSScadaJava
SKS class excercise. A n-tier application with multiple clients and web services, built on Java EE.