Unofficial pages of the Deep Learning course at UniZg-FER

About the course


Currently we only offer lectures in Croatian. We cover the following subjects: The chapters and sections refer to the textbook by Goodfellow et al.


  1. Ian Goodfellow, Yoshua Bengio and Aaron Courville. Deep Learning. MIT Press (html)
  2. Michael Nielsen. Neural Networks and Deep Learning. Determination press. (html)


Our exams typically consist of 12 short theoretical questions (you need to choose a corect answer, 30% points) and 5-6 problems (70% points). To get a feeling on how the problems might look like, please have a look at our previous exams listed below. These documents are in Croatian, however Google translate does a pretty good job these days, so I think they might be helpful.

  1. Midleterm exam 2016/17 (pdf)
  2. Final exam 2016/17 (pdf)

Laboratory exercises

  1. Logistic regression, gradient descent, Python, numpy: instructions.
  2. Tensorflow, fully connected models, MNIST: instructions;
  3. Convolutional models, MNIST, CIFAR: instructions;
  4. Recurrent models: instructions.
  5. Generative models: instructions.

Student projects

Interesting links