Check Our Latest
As a main objective in Artificial Intelligence, there are increasing need for building intelligent agents with learning capability, in many applications like Medical Diagnosis, Text/Web classification, Computer Vision, Voice-related Analysis and Applications, Spoken Language Understanding, Data Mining, Economical Predictions, Natural Language Processing/Understanding, Machine Translation, Autonomous Navigation, and Business Software. Recently, Intelligent Learning Systems, including Deep Learning models, have been successfully applied in most of the above-mentioned applications, and achieved significant superior results.
From the theoretical point of view, design and analysis of intelligent models and algorithms in Machine Learning field, have close relationships with several fundamental mathematical subjects like Linear/Non-Linear Optimization, Convergence Study of Iterative Numerical Methods, Estimation Theory, Euclidean and Riemannian Vector Spaces Geometry, Statistical Learning Theory, Stochastic Processes, Decision Theory, and Performance Evaluation of Predictive Models.
From the other viewpoint, a prominent approach in implementing intelligent systems in real-world environments with high complexities, is applying Computational Intelligence algorithms. These algorithms typically work by avoiding the simplifying assumptions about the problem in hand, which are usual in machine learning algorithms, and provide possibilities to achieve more practical solutions.
The mission of Intelligent and Learning Systems (ILS) Research Laboratory is to develop learning algorithms in intelligent systems from both of the theoretical and practical aspects. ILS Lab has currently been focused on development of novel learning methods with deep, multimodal, geometric, and data insufficiency compensating approaches.
Machine Learning and Pattern Recognition
Computer Vision and Image Understanding
Statistical Learning Theory
Data Manifold Analysis
Geometric Deep Learning
Multimodal Data Analysis
Distance Metric Learning
Transfer Learning and Domain Adaptation
Self-Supervised and Semi-Supervised Learning
Estimation of Distribution Algorithms
Intelligent Digital Health
Probabilistic Graphical Models
Deep Reinforcement Learning
Data Analysis and Modeling
Graph Neural Network,
Natural Language Processing
Intelligent Neural Networks