Investigación | 🇬🇧 Research

Probabilistic Machine Learning for Healthcare

Probabilistic Machine Learning for Healthcare

Machine learning can be used to make sense of healthcare data. Probabilistic machine learning models help provide a complete picture of observed data in healthcare. In this review, we examine how probabilistic machine learning can advance healthcare. We consider challenges in the predictive model building pipeline where probabilistic models can be beneficial including calibration and missing data. Beyond predictive models, we also investigate the utility of probabilistic machine learning models in phenotyping, in generative models for clinical use cases, and in reinforcement learning.

Probabilistic Machine Learning for Healthcare Leer más »

Páginas: 1 2 3
Tidy Modeling with R

Tidy Modeling with R

This book provides an introduction to how to use our software to create models. We focus on a dialect of R called the tidyverse that is designed to be a better interface for common tasks using R. If you’ve never heard of or used the tidyverse, Chapter 2 provides an introduction. In this book, we demonstrate how the tidyverse can be used to produce high quality models. The tools used to do this are referred to as the tidymodels packages

Tidy Modeling with R Leer más »

Páginas: 1 2 3
The future of AI

The future of AI

If you wonder what is next in the evolution towards general AI then this session is for you. We have seen some painful failures of artificial intelligence pointing to a lack of ‘common sense’. Are neural networks really the solution we seek or is a new path needed? Find out what IBM Research is cooking in terms of hardware and software in the never ending quest towards General AI.

The future of AI Leer más »

Páginas: 1 2
TextAttack: A Framework for Adversarial Attacks, Data Augmentation, and Adversarial Training in NLP

TextAttack: A Framework for Adversarial Attacks, Data Augmentation, and Adversarial Training in NLP

This paper introduces TextAttack, a Python framework for adversarial attacks, data augmentation, and adversarial training in NLP. TextAttack builds attacks from four components: a goal function, a set of constraints, a transformation, and a search method. TextAttack’s modular design enables researchers to easily construct attacks from combinations of novel and existing components. TextAttack provides implementations of 16 adversarial attacks from the literature and supports a variety of models and datasets, including BERT and other transformers, and all GLUE tasks.

TextAttack: A Framework for Adversarial Attacks, Data Augmentation, and Adversarial Training in NLP Leer más »

Páginas: 1 2 3
Diagnostic uncertainty calibration: towards reliable machine predictions in medical domain

Diagnostic uncertainty calibration: towards reliable machine predictions in medical domain

We further formalize the metrics for higher-order statistics, including inter-rater disagreement, in a unified way, which enables us to assess the quality of distributional uncertainty. In addition, we propose a novel post-hoc calibration method that equips trained neural networks with calibrated distributions over class probability estimates. With a large-scale medical imaging application, we show that our approach significantly improves the quality of uncertainty estimates in multiple metrics.

Diagnostic uncertainty calibration: towards reliable machine predictions in medical domain Leer más »

Páginas: 1 2 3