MUH-920 Mühendislikte Yapay Zeka Uygulamaları. Undergraduate faculty-wide common elective course, Süleyman Demirel University
Prof. Dr. Utku Kose, Süleyman Demirel University
The course site opens every week of MUH-920. Each card leads to the week overview on GitHub, with the learning outcomes, the study path and the tasks of the week, and to its lecture page, interactive lab, Colab notebook and printable notes. The repository README describes the course and how its materials fit together, and the syllabus states its outcomes, assessment and policies.
Progress in reading checks and self-assessments is stored in this browser only and shown on each week card.
Start here: Python warm-up in Colab Repository Syllabus
Week 1
Python step 1: Values, variables and decisions
Lab: Agent workbench: Heating a room through a winter week
Week 2
Python step 2: Lists, tuples and loops
Lab: Path planning playground: Search on grids and terrain
Week 3
Python step 3: Dictionaries and functions
Lab: Rule-based reasoning lab: Soil classification and pump diagnosis
Week 4
Python step 4: NumPy arrays and first plots
Lab: Fuzzy controller designer: Tank level control
Week 5
Python step 5: Random numbers, arrays and genetic operators
Lab: Evolution lab: Genetic algorithms, differential evolution and Pareto fronts
Week 6
Python step 6: Classes, objects and probabilistic choice
Lab: Swarm lab: Particles, a motor controller and an ant colony
Week 7
Python step 7: Tables with pandas and honest evaluation with scikit-learn
Lab: Regression studio: Complexity, validation and leakage
Week 8
Python step 8: Grouping, counting and evaluation functions
Lab: Threshold and cost lab: From scores to decisions
Week 9
Python step 9: Signals, features and clustering with NumPy
Lab: Unsupervised lab: Clusters and a vibration analyser
Week 10
Python step 10: Matrices, shapes and tensors
Lab: Neural network playground: Neurons, networks and optimisers
Week 11
Python step 11: Images, batches and network classes
Lab: Convolution explorer: Filters, feature maps and receptive fields
Week 12
Python step 12: Time-indexed data, baselines and exceptions
Lab: Forecast workbench: Baselines, smoothing and honest evaluation
Week 13
Python step 13: Text, vectors and attention
Lab: Language lab: Tokens, sampling and grounded retrieval
Midterm project (end of Week 7) and final project (end of Week 14), with starter notebooks and a common report template.