Search Results for author:
Found 9 papers, 8 papers with code
Language models scale reliably with over-training and on downstream tasks
We fit scaling laws that extrapolate in both the number of model parameters and the ratio of training tokens to parameters.
Optimal Sparse Survival Trees
Interpretability is crucial for doctors, hospitals, pharmaceutical companies and biotechnology corporations to analyze and make decisions for high stakes problems that involve human health.
Inferior Alveolar Nerve Segmentation in CBCT images using Connectivity-Based Selective Re-training
Inferior Alveolar Nerve (IAN) canal detection in CBCT is an important step in many dental and maxillofacial surgery applications to prevent irreversible damage to the nerve during the procedure. The ToothFairy2023 Challenge aims to establish a 3D maxillofacial dataset consisting of all sparse labels and partial dense labels, and improve the ability of automatic IAN segmentation.
Optimal Sparse Regression Trees
Regression trees are one of the oldest forms of AI models, and their predictions can be made without a calculator, which makes them broadly useful, particularly for high-stakes applications.
TimberTrek: Exploring and Curating Sparse Decision Trees with Interactive Visualization
Given thousands of equally accurate machine learning (ML) models, how can users choose among them?
Exploring the Whole Rashomon Set of Sparse Decision Trees
We show three applications of the Rashomon set: 1) it can be used to study variable importance for the set of almost-optimal trees (as opposed to a single tree), 2) the Rashomon set for accuracy enables enumeration of the Rashomon sets for balanced accuracy and F1-score, and 3) the Rashomon set for a full dataset can be used to produce Rashomon sets constructed with only subsets of the data set.
Materials Transformers Language Models for Generative Materials Design: a benchmark study
We also find that the properties of the generated samples can be tailored by training the models with selected training sets such as high-bandgap materials.
Multitask Learning for Citation Purpose Classification
The goal of the competition is to classify a citation in a scientific article based on its purpose.
Active learning based generative design for the discovery of wide bandgap materials
Our experiments show that while active learning itself may sample chemically infeasible candidates, these samples help to train effective screening models for filtering out materials with desired properties from the hypothetical materials created by the generative model.
