Deep Function

Deep function research focuses on developing and understanding neural network architectures capable of learning complex, high-dimensional functions from diverse data types, including functional data and images. Current efforts concentrate on improving model robustness and generalization, particularly in scenarios with imbalanced or limited data, through techniques like deep metric learning and incorporating prior knowledge. This work is significant for advancing machine learning capabilities in various applications, such as defect detection in manufacturing, reinforcement learning, and knowledge graph embedding, by enabling more accurate and efficient function approximation.

Papers

July 5, 2024

RPN: Reconciled Polynomial Network Towards Unifying PGMs, Kernel SVMs, MLP and KAN
Jiawei Zhang
Kolmogorov Arnold Network Markov Chain Probabilistic Graphical Model Multi Layer Perceptron Novel Deep Learning Model Polynomial Network Deep Function

April 4, 2024

DeepFunction: Deep Metric Learning-based Imbalanced Classification for Diagnosing Threaded Pipe Connection Defects using Functional Data
Yukun Xie, Juan Du, Chen Zhang
Deep Metric Learning Functional Data Analysis Defect Classification Defect Sample Pipe Inspection Defect Class Deep Function

March 7, 2024

Vlearn: Off-Policy Learning with Efficient State-Value Function Estimation
Fabian Otto, Philipp Becker, Ngo Anh Vien, Gerhard Neumann
Policy Learning Policy Reinforcement Learning Policy Deep Reinforcement Learning State Action Value Deep Function

February 23, 2023

SPINDLE: Spinning Raw Text into Lambda Terms with Graph Attention
Konstantinos Kogkalidis, Michael Moortgat, Richard Moot
Graph Attention Multimodal Reasoning Document Parsing Construction Grammar Lambda Calculus Raw Text Deep Function Spindle Annotation

January 23, 2023

Utilizing Domain Knowledge: Robust Machine Learning for Building Energy Prediction with Small, Inconsistent Datasets
Xia Chen, Manav Mahan Singh, Philipp Geyer
Machine Learning Domain Knowledge Data Efficient Deep Function

November 9, 2022

DeepE: a deep neural network for knowledge graph embedding
Zhu Danhao, Shen Si, Huang Shujian, Yin Chang, Ding Ziqi
Deep Neural Network Knowledge Graph Deep Model Deep Feature Deeper Network Deep Function

May 23, 2022

When Data Geometry Meets Deep Function: Generalizing Offline Reinforcement Learning
Jianxiong Li, Xianyuan Zhan, Haoran Xu, Xiangyu Zhu, Jingjing Liu, Ya-Qin Zhang
Offline Reinforcement Learning Policy Learning Deep Q Network Geometric Data Deep Function

February 5, 2022

Decision boundaries and convex hulls in the feature space that deep learning functions learn from images
Roozbeh Yousefzadeh
Image Classification Feature Space Digital Image Decision Boundary Low Dimensional Manifold Image Classification Model Convex Hull Dimensional Space Deep Function

Deep Function

Papers

RPN: Reconciled Polynomial Network Towards Unifying PGMs, Kernel SVMs, MLP and KAN

DeepFunction: Deep Metric Learning-based Imbalanced Classification for Diagnosing Threaded Pipe Connection Defects using Functional Data

Vlearn: Off-Policy Learning with Efficient State-Value Function Estimation

SPINDLE: Spinning Raw Text into Lambda Terms with Graph Attention

Utilizing Domain Knowledge: Robust Machine Learning for Building Energy Prediction with Small, Inconsistent Datasets

DeepE: a deep neural network for knowledge graph embedding

When Data Geometry Meets Deep Function: Generalizing Offline Reinforcement Learning

Decision boundaries and convex hulls in the feature space that deep learning functions learn from images