top of page
Automated Machine Learning Lab
Current Research Topics
Metalearning and Automatic Model Recommendation Based on Knowledge-base
Publications List:
Meta-Features and Auto Feature Selection\Generation
Publications List:
Optimal Machine Learning Pipeline Search and Recommendation
Publications List:
-
RankML: a Meta Learning-Based Approach for Pre-Ranking Machine Learning Pipelines
-
DeepLine: AutoML Tool for Pipelines Generation using Deep Reinforcement Learning and Hierarchical Actions Filtering
Explainability of the Models\Instances
Neural Network Architecture Search
-
Source Model Selection for Deep Learning in the Time Series Domain
-
A meta-learning Approach for Image Classification Architecture Recommendation
Additional Research Topics
-
Model Robustness (general and over time)
-
Data Augmentation
-
Learning on Budget
-
Model Compression
Lab Research Team
bottom of page