Search Results for author:
Found 51 papers, 30 papers with code
Confidence intervals uncovered: Are we ready for real-world medical imaging AI?
For more than 60% of papers, the mean performance of the second-ranked method was within the CI of the first-ranked method.
What is the Role of Small Models in the LLM Era: A Survey
Large Language Models (LLMs) have made significant progress in advancing artificial general intelligence (AGI), leading to the development of increasingly large models such as GPT-4 and LLaMA-405B.
Imputation for prediction: beware of diminishing returns
Missing values are prevalent across various fields, posing challenges for training and deploying predictive models.
Teaching Models To Survive: Proper Scoring Rule and Stochastic Optimization with Competing Risks
When data are right-censored, i. e. some outcomes are missing due to a limited period of observation, survival analysis can compute the "time to event".
CARTE: Pretraining and Transfer for Tabular Learning
The architecture -- CARTE for Context Aware Representation of Table Entries -- uses a graph representation of tabular (or relational) data to process tables with different columns, string embedding of entries and columns names to model an open vocabulary, and a graph-attentional network to contextualize entries with column names and neighboring entries.
Reconfidencing LLMs from the Grouping Loss Perspective
In this work, we construct a new evaluation dataset derived from a knowledge base to assess confidence scores given to answers of Mistral and LLaMA.
Learning High-Quality and General-Purpose Phrase Representations
The framework employs phrase type classification as an auxiliary task and incorporates character-level information more effectively into the phrase representation.
Vectorizing string entries for data processing on tables: when are larger language models better?
We study the benefits of language models in 14 analytical tasks on tables while varying the training size, as well as for a fuzzy join benchmark.
The Locality and Symmetry of Positional Encodings
Positional Encodings (PEs) are used to inject word-order information into transformer-based language models.
Causal thinking for decision making on Electronic Health Records: why and how
We illustrate the various choices in studying the effect of albumin on sepsis mortality in the Medical Information Mart for Intensive Care database (MIMIC-IV).
Understanding metric-related pitfalls in image analysis validation
Validation metrics are key for the reliable tracking of scientific progress and for bridging the current chasm between artificial intelligence (AI) research and its translation into practice.
GLADIS: A General and Large Acronym Disambiguation Benchmark
Acronym Disambiguation (AD) is crucial for natural language understanding on various sources, including biomedical reports, scientific papers, and search engine queries.
How to select predictive models for causal inference?
But does computing these nuisance adds noise to model selection?
Beyond calibration: estimating the grouping loss of modern neural networks
Yet calibration is not enough: even a perfectly calibrated classifier with the best possible accuracy can have confidence scores that are far from the true posterior probabilities.
Why do tree-based models still outperform deep learning on tabular data?
While deep learning has enabled tremendous progress on text and image datasets, its superiority on tabular data is not clear.
Metrics reloaded: Recommendations for image analysis validation
The framework was developed in a multi-stage Delphi process and is based on the novel concept of a problem fingerprint - a structured representation of the given problem that captures all aspects that are relevant for metric selection, from the domain interest to the properties of the target structure(s), data set and algorithm output.
Imputing Out-of-Vocabulary Embeddings with LOVE Makes Language Models Robust with Little Cost
State-of-the-art NLP systems represent inputs with word embeddings, but these are brittle when faced with Out-of-Vocabulary (OOV) words.
Benchmarking missing-values approaches for predictive models on health databases
Using gradient-boosted trees, we compare native support for missing values with simple and state-of-the-art imputation prior to learning.
Label scarcity in biomedicine: Data-rich latent factor discovery enhances phenotype prediction
High-quality data accumulation is now becoming ubiquitous in the health domain.
Preventing dataset shift from breaking machine-learning biomarkers
When a dataset shift occurs, standard machine-learning techniques do not suffice to extract and validate biomarkers.
What's a good imputation to predict with missing values?
In fact, we show that on perfectly imputed data the best regression function will generally be discontinuous, which makes it hard to learn.
Common Limitations of Image Processing Metrics: A Picture Story
While the importance of automatic image analysis is continuously increasing, recent meta-research revealed major flaws with respect to algorithm validation.
How I failed machine learning in medical imaging -- shortcomings and recommendations
Finally we provide a broad range of recommendations on how to further these address problems in the future.
Accounting for Variance in Machine Learning Benchmarks
Strong empirical evidence that one machine-learning algorithm A outperforms another one B ideally calls for multiple trials optimizing the learning pipeline over sources of variation such as data sampling, data augmentation, parameter initialization, and hyperparameters choices.
A Lightweight Neural Model for Biomedical Entity Linking
Biomedical entity linking aims to map biomedical mentions, such as diseases and drugs, to standard entities in a given knowledge base.
NeuMiss networks: differentiable programming for supervised learning with missing values
We provide an upper bound on the Bayes risk of NeuMiss networks, and show that they have good predictive accuracy with both a number of parameters and a computational complexity independent of the number of missing data patterns.
Fine-grain atlases of functional modes for fMRI analysis
We demonstrate the benefits of extracting reduced signals on our fine-grain atlases for many classic functional data analysis pipelines: stimuli decoding from 12, 334 brain responses, standard GLM analysis of fMRI across sessions and individuals, extraction of resting-state functional-connectomes biomarkers for 2, 500 individuals, data compression and meta-analysis over more than 15, 000 statistical maps.
NeuroQuery: comprehensive meta-analysis of human brain mapping
Reaching a global view of brain organization requires assembling evidence on widely different mental processes and mechanisms.
Linear predictor on linearly-generated data with missing values: non consistency and solutions
In the particular Gaussian case, it can be written as a linear function of multiway interactions between the observed data and the various missing-value indicators.
What’s in a functional brain parcellation?
Here we consider atlases used to parcellate the brain when studying brain function.
Encoding high-cardinality string categorical variables
We introduce two encoding approaches for string categories: a Gamma-Poisson matrix factorization on substring counts, and the min-hash encoder, for fast approximation of string similarities.
On the consistency of supervised learning with missing values
A striking result is that the widely-used method of imputing with a constant, such as the mean prior to learning is consistent when missing values are not informative.
Extracting representations of cognition across neuroimaging studies improves brain decoding
Analyzing data across studies could bring more statistical power; yet the current brain-imaging analytic framework cannot be used at scale as it requires casting all cognitive tasks in a unified theoretical framework.
Approximate message-passing for convex optimization with non-separable penalties
We introduce an iterative optimization scheme for convex objectives consisting of a linear loss and a non-separable penalty, based on the expectation-consistent approximation and the vector approximate message-passing (VAMP) algorithm.
Similarity encoding for learning with dirty categorical variables
We show that a simple approach that exposes the redundancy to the learning algorithm brings significant gains.
Text to brain: predicting the spatial distribution of neuroimaging observations from text reports
In this paper, we propose to mine brain medical publications to learn the spatial distribution associated with anatomical terms.
Learning Neural Representations of Human Cognition across Many fMRI Studies
Cognitive neuroscience is enjoying rapid increase in extensive public brain-imaging datasets.
Cross-validation failure: small sample sizes lead to large error bars
Predictive models ground many state-of-the-art developments in statistical brain image analysis: decoding, MVPA, searchlight, or extraction of biomarkers.
Subsampled online matrix factorization with convergence guarantees
We present a matrix factorization algorithm that scales to input matrices that are large in both dimensions (i. e., that contains morethan 1TB of data).
Deriving reproducible biomarkers from multi-site resting-state data: An Autism-based example
These R-fMRI pipelines build participant-specific connectomes from functionally-defined brain areas.
Recursive nearest agglomeration (ReNA): fast clustering for approximation of structured signals
Our goal is to summarize the data to decrease computational costs and memory footprint of subsequent analysis.
Social-sparsity brain decoders: faster spatial sparsity
Spatially-sparse predictors are good models for brain decoding: they give accurate predictions and their weight maps are interpretable as they focus on a small number of regions.
Assessing and tuning brain decoders: cross-validation, caveats, and guidelines
Decoding, ie prediction from brain images or signals, calls for empirical evaluation of its predictive power.
Learning to Discover Sparse Graphical Models
Learning this function brings two benefits: it implicitly models the desired structure or sparsity properties to form suitable priors, and it can be tailored to the specific problem of edge structure discovery, rather than maximizing data likelihood.
Dictionary Learning for Massive Matrix Factorization
Sparse matrix factorization is a popular tool to obtain interpretable data decompositions, which are also effective to perform data completion or denoising.
Ranked #13 on
Recommendation Systems
on MovieLens 10M
Compressed Online Dictionary Learning for Fast fMRI Decomposition
We present a method for fast resting-state fMRI spatial decomposi-tions of very large datasets, based on the reduction of the temporal dimension before applying dictionary learning on concatenated individual records from groups of subjects.
Testing for Differences in Gaussian Graphical Models: Applications to Brain Connectivity
We characterize the uncertainty of differences with confidence intervals obtained using a parametric distribution on parameters of a sparse estimator.
FAASTA: A fast solver for total-variation regularization of ill-conditioned problems with application to brain imaging
The total variation (TV) penalty, as many other analysis-sparsity problems, does not lead to separable factors or a proximal operatorwith a closed-form expression, such as soft thresholding for the $\ell\_1$ penalty.
Mapping cognitive ontologies to and from the brain
Imaging neuroscience links brain activation maps to behavior and cognition via correlational studies.
API design for machine learning software: experiences from the scikit-learn project
Scikit-learn is an increasingly popular machine learning li- brary.
Scikit-learn: Machine Learning in Python
Scikit-learn is a Python module integrating a wide range of state-of-the-art machine learning algorithms for medium-scale supervised and unsupervised problems.
