Deep Regression

Deep regression uses deep learning models to predict continuous values, aiming to improve accuracy and efficiency compared to traditional regression methods. Current research focuses on enhancing model robustness and uncertainty quantification, employing architectures like convolutional neural networks, recurrent neural networks (LSTMs), and Gaussian processes, often combined with techniques like ensemble methods and post-hoc calibration. This field is significant for its applications across diverse domains, including medical imaging, agriculture, and materials science, enabling more accurate predictions and improved decision-making in these areas.

Papers

February 24, 2022

Temporal Convolution Domain Adaptation Learning for Crops Growth Prediction
Shengzhe Wang, Ling Wang, Zhihao Lin, Xi Zheng
Domain Adaptation Deep Regression Crop Yield Prediction

December 2, 2021

Dimension-Free Average Treatment Effect Inference with Deep Neural Networks
Xinze Du, Yingying Fan, Jinchi Lv, Tianshu Sun, Patrick Vossler
Deep Neural Network Treatment Effect Deep Regression Average Treatment Effect Regression Function Deep Neural Network Estimator DNN Prediction

November 23, 2021

Uncertainty estimation under model misspecification in neural network regression
Maria R. Cervera, Rafael Dätwyler, Francesco D'Angelo, Hamza Keurti, Benjamin F. Grewe, Christian Henning
Uncertainty Estimation Aleatoric Uncertainty Deep Regression Model Misspecification Flexible Model

Deep Regression

Papers

Temporal Convolution Domain Adaptation Learning for Crops Growth Prediction

Dimension-Free Average Treatment Effect Inference with Deep Neural Networks

Uncertainty estimation under model misspecification in neural network regression