Artificial Intelligence Engineering

Required Courses

The aim of this course is to teach you the fundamental topics in data science in order to help you get prepared for advanced topics. Firstly, we will discuss causality and experimental research. Subsequently, we will teach the programming skills required for data analysis including programming in Python, DataFrames, and visualization. Next, we will see the topics of randomness, sampling, testing hypotheses, comparing two samples, estimation, and why the mean matters. Finally, we will make a very brief introduction to machine learning and see the topics of prediction, classification, and Bayes Theorem.

Who are you, what is critical thinking, what is truth, what is knowledge, how good are your ideas, basic problem "mine is better", resistance to change, relevance, face-saving, stereotypical, oversimplification, hasty conclusions, baseless assumptions, logical errors, the problem of combination,  knowing yourself, being an observer, clarifying issues, doing research, interpreting evidence, analyzing viewpoints, forming judgments, biases, logical fallacies, cognitive distortions

Intelligent agents, search methods in problem solving, informed and uninformed search methods, discovery methods, constraint satisfaction problems, game playing, knowledge and reasoning, inference, first order logic, knowledge representation, learning.

Deep Learning Fundamentals, Deep Neural Networks, Deep Learning Training Models, Convolutional Neural Networks (CNN), Auto Encoder (AE), Recurrent Neural Networks (RNN), Generator Adversarial Networks (GAN), Transformer Networks, Deep Reinforcement Learning, Deep Learning Applications

Introduction and definitions, classification / regression problem, supervised learning, linear regression, least squares error sum, logistic regression, perceptron, bias-variance, regulation, over-fitting, feature selection, extraction, artificial neural networks, decision trees, support vector machines, ensemble networks, unsupervised learning

Students will be informed and motivated by expert guest speakers on innovative artificial intelligence applications, success stories, entrepreneurship opportunities, future trends. The students are expected to define their graduation project on artificial intelligence and data science in the next semester and complete the first stages (requirements analysis, selection of technologies to be used, supply of data sets, tools, materials, general system architecture, etc.).

In this course, students conduct an artificial intelligence or data science project. Within the scope of this project, literature review, problem formulation, data and field research and a comprehensive design are generated for the solution of an artificial intelligence problem. The result of the design is presented to the project manager in the desired form at the end of the semester. Introduction, Planning, Modeling, System Construction, Development of the artificial intelligence application, Final demo.

Elective Courses

The aim of this course is to equip you with the principles of derivative pricing and numerical methods used to solve stochastic problems in finance. The course will teach you the basic numerical techniques of finance, lattice, finite difference, Monte-Carlo simulation and density transformation methods. After preparing you on the Black-Scholes option pricing framework, the course will include numerical methods, simple and exotic options, real options, credit risk and risk-free bond pricing for the derivative products and bond pricing problems.

The aim of this course is to equip you with quantitative models and big data analytics in finance. This course will provide you with regression analysis; robustness analysis; Monte Carlo simulation; linear, integer and nonlinear optimization; and financial modeling frameworks, tools, and methodology concepts such as lattice methods. The course covers these concepts, classical finance problems mean-variance portfolio selection; bond portfolio management; maturity structure estimation; capital budgeting; risk measurement; discounted cash flow risk analysis; Sensitivity analysis to European and American options pricing problems and big data issues; high frequency trading; and applies these topics to big data and fin-tech companies.

Within the scope of this course, it is aimed to conduct theoretical or applied research on artificial intelligence / machine learning together with the academic advisor. At the end of the term, the aim is to create a publication (conference or journal) about the researches and studies carried out.

Within the scope of this course, it is aimed to conduct theoretical or applied research on artificial intelligence / machine learning together with the academic advisor. In general, it will be evaluated as a continuation of the work carried out within the scope of YAP 490, and the aim is to create an article in an indexed journal about the researches and studies carried out at the end of the semester.