Home
Instructor
A.Nurdan SARAN
Office#: L-219 Tel: 2331342 E-mail: buz[AT]cankaya.edu.tr
Office Hour: Monday 13:20-14:10
Course Content
Overview of the artificial neural networks, forms of neural networks and underlying ideas, the training algorithms, backpropagation, feedforward and recurrent networks. The main concepts in designing neural networks, and their main application areas are introduced as well.
Aim of the Course:
This course is proposed for providing the basis for neural networks concepts, algorithms and techniques for the undergraduate 3rd and 4th year students. At the end of the course, they are expected to prepare and present a project to demonstrate their solid understanding of applying neural network techniques on a well-defined problem.
Prerequisites
- Basic Math skills: Linear algebra, probability
- Chapters 1-4 of: http://www.deeplearningbook.org
- Mathematics for Machine Learning: https://www.youtube.com/playlist?list=PL05umP7R6ij1a6KdEy8PVE9zoCv6SlHRS
- Python coding skills ( PyTorch /Tensorflow/MXNet)
Text Book
- Zhang, Lipton, Li, Smola: Dive into Deep Learning
- Martin T. Hagan , "Neural Network Design"
Reference Books
- Goodfellow, Bengio and Courville: Deep Learning
- Bishop: Pattern Recognition and Machine Learning
- Deisenroth, Faisal and Ong: Mathematics for Machine Learning
Grading
- Midterm 30 %
- Homework+Project 40 %
- Final 30 %