About Me
Linear and Integer Programming;
Mathematical Preliminaries
The Linear Decision Model, Applications of Linear Programming
The Conventional Linear Programming Model
Foundations of the Simplex Method
The Simplex Method: Tableau and Computation
Special Simplex Implementations Duality
Deep Learning
Deep learning is a newly emerged area of research in machine learning and has recently shown huge success in a variety of areas. The impact on many applications is revolutionary, which ignites intensive studies of this topic.
During the past few decades, the prevalent machine learning methods, including support vector machines, conditional random fields, hidden Markov models, and one-hidden-layer multi-layer perceptron, have found a broad range of applications. While being effective in solving simple or well-constrained problems, these methods have one drawback in common, namely they all have shallow architectures. They in general have no more than one or two layers of nonlinear feature transformations, which limits their performance on many real-world applications.On the contrary, the human brain and its cognitive process, being far more complicated, have deep architectures that are organized into many hierarchical layers. The information gets more abstract while going up along the hierarchy. Interests in using deep architectures were reignited in 2006 when a deep belief network was shown to be trained well. Since then deep learning methods and applications have witnessed unprecedented success.This course will give an introduction to deep learning both by presenting valuable methods and by addressing specific applications.
This course covers both theory and practices for deep learning.
Topics will include
Machine learning fundamentals
Deep learning concepts
Deep learning methods including deep autoencoders, deep neural networks, recurrent neural networks, long short-term memory recurrent networks, convolutional neural networks, and generative adversarial networks.
Selected applications of deep learning
Control and Optimization;
Optimal control is the problem of finding control for a dynamic system such that a certain performance function is minimized. The subject stems from the calculus of variations. The prompt development of optimal control in 1950s owns two inventions: the maximum principle by L.S. Pontryagin and dynamic programming by R. Bellman. Today, the stress is on developing efficient numerical methods for solving a class of optimal control problems (herein convex optimization).
Fracture Mechanics for Laminated Composite Structures
Theory and practice related to fracture mechanical problems for laminated composite structures, such as wind turbine blades. The classical approach to fracture mechanics will be presented and extended to anisotropic and bi-material problems via analytical and numerical methods including the framework of cohesive zone modeling. Furthermore, practical aspects of laboratory testing in relation to determination of fracture mechanical properties will be covered and included in the exercises for the course as experiments. The course consists of four parts; lectures, exercises, laboratory testing, and an informal poster session. The net work load corresponds to 5 ECTS. The exercises will consist of analytical problems solved using math programs such as Maple, numerical problems solved using the Finite Element Program ANSYS, and laboratory exercises conducted in the Lab of AAU. For the poster session all participants are expected to upload a poster of their own work, project or similar, which include discussion of how fracture mechanics apply. This poster should be uploaded to the organizers a week before the start of the course.
Classical fracture mechanics
Bi-material fracture mechanics
Anisotropic materials
Numerical estimation of fracture mechanical parameters with the finite element method (FEM)
R-curve effects
Crack bridging
Cohesive zone modeling
Numerical implementation of cohesive zone models in FEM
Experimental estimation of fracture mechanical properties
Fatigue properties of laminated composites
Subjects
Tutoring and Designing Options
Think Concept, Planning and Design, Process, Research, and Product Made.
One on One Lessons:
Machine Learning and Robotic
Rate: $50,000/hr
Group Sessions:
Location
Tulungagung, and Malang, Indonesia
Optimal and Stochastic Control
Rate: $50,000/hr