Explicit Feature Map

Explicit feature maps are transformations that project data into a lower-dimensional space, aiming to improve model performance and interpretability. Current research focuses on developing learnable explicit feature maps (LEFMs) that are integrated into existing deep learning architectures, such as UNet and DeepLabv3+, primarily for image segmentation tasks in medical imaging. This approach seeks to enhance model accuracy while simultaneously increasing the explainability of predictions, addressing a key challenge in complex deep learning models. The resulting improvements in performance and interpretability have significant implications for various applications, particularly in fields requiring high accuracy and transparent decision-making processes like medical diagnosis.

Papers

October 26, 2024

Neural Fields in Robotics: A Survey
Muhammad Zubair Irshad, Mauro Comi, Yen-Chen Lin, Nick Heppert, Abhinav Valada, Rares Ambrus, Zsolt Kira, Jonathan Tremblay
Timely Survey Computer Vision Neural Radiance Field Robotics Domain Neural Field Explicit Feature Map

October 16, 2024

An Exact Finite-dimensional Explicit Feature Map for Kernel Functions
Kamaledin Ghiasi-Shirazi, Mohammadreza Qaraei
Kernel Method Kernel Function Laplacian Kernel Explicit Feature Map

November 1, 2023

Pretraining Data Mixtures Enable Narrow Model Selection Capabilities in Transformer Models
Steve Yadlowsky, Lyric Doshi, Nilesh Tripuraneni
Large Language Model Transformer Model Sequence Model Pre Training Model Explicit Feature Map

August 31, 2023

On the Equivalence between Implicit and Explicit Neural Networks: A High-dimensional Viewpoint
Zenan Ling, Zhenyu Liao, Robert C. Qiu
Neural Tangent Kernel High Dimension Shallow Network Implicit Language Implicit Neural Network Explicit Feature Map

April 14, 2022

LEFM-Nets: Learnable Explicit Feature Map Deep Networks for Segmentation of Histopathological Images of Frozen Sections
Dario Sitnik, Ivica Kopriva
High Dimensional Segmentation Based Approach Deep Network Histopathological Image Explicit Feature Map

March 7, 2022

Clustering and classification of low-dimensional data in explicit feature map domain: intraoperative pixel-wise diagnosis of adenocarcinoma of a colon in a liver
Dario Sitnik, Ivica Kopriva
Classification Code Inherent Interpretability Linear Classifier Surgical Scene Segmentation Low Dimensional Data Explicit Feature Map

February 21, 2022

Imbalanced Classification via Explicit Gradient Learning From Augmented Data
Bronislav Yasinnik, Moshe Salhov, Ofir Lindenbaum, Amir Averbuch
Deep Learning Data Imbalance Imbalanced Classification Augmented Data Underrepresented Group Minority Sample Explicit Feature Map

January 28, 2022

Continuous Deep Equilibrium Models: Training Neural ODEs faster by integrating them to Infinity
Avik Pal, Alan Edelman, Christopher Rackauckas
Neural ODE Implicit Model Deep Equilibrium Model Implicit Layer Explicit Feature Map

Explicit Feature Map

Papers

Neural Fields in Robotics: A Survey

An Exact Finite-dimensional Explicit Feature Map for Kernel Functions

Pretraining Data Mixtures Enable Narrow Model Selection Capabilities in Transformer Models

On the Equivalence between Implicit and Explicit Neural Networks: A High-dimensional Viewpoint

LEFM-Nets: Learnable Explicit Feature Map Deep Networks for Segmentation of Histopathological Images of Frozen Sections

Clustering and classification of low-dimensional data in explicit feature map domain: intraoperative pixel-wise diagnosis of adenocarcinoma of a colon in a liver

Imbalanced Classification via Explicit Gradient Learning From Augmented Data

Continuous Deep Equilibrium Models: Training Neural ODEs faster by integrating them to Infinity