ML Lab
Research laboratory

Machine
Learning Lab

How do machines learn structure from data, and when can we trust what they learn?

Explore research ↓
Fig. 01 / Model landscape

Research directions

Representation learning

How does a model decide which features of a complex signal matter?

Example experiment

One way to probe a learned representation is to freeze the encoder and test which attributes a simple classifier can recover.

Graph learning

How do relationships between observations change a prediction?

Example experiment

Compare a graph model with a feature-only baseline, then shuffle the edges to test how much information the connectivity contributes.

Model evaluation

What happens to a model when the data change?

Example experiment

Hold out a collection site or time period and compare performance and calibration with the original test set.

People

Asst. Prof. Cemre Candemir

Students

  • Enes Talay
  • Oğuz Kuru
  • Yağmur Dalkıran
  • Maşallah Demirhan
  • Ragıp Günay
  • Fahreddin Hepdonduran
  • Fulya Çakıroğlu
  • Erdem Aslan
  • Figen Koç
  • Uğur Kandemiş
  • Göksel Sina

Publications

  • IEEE 11728052

    Machine Learning-Based Spoken Digit Recognition: A Comparative Study of Voting, Stacking and Late Fusion

    Münif Zeybek, Sekou J. Massalay, Cemre Candemir

    10th International Artificial Intelligence and Data Processing Symposium (IDAP), 2026.

  • IEEE 11727885

    MAMORI: A Cross-Lingual Benchmark for Indirect Prompt Injection in Tool-Using LLM Agents

    Hayder Almamoori, Cemre Candemir

    10th International Artificial Intelligence and Data Processing Symposium (IDAP), 2026.

  • IEEE 11632530

    Sentiment Analysis of Turkish Texts Using Graph Convolutional Neural Networks and Bert Language Model

    Canan Kocatürk, Cemre Candemir, and İlker Kocabaş

    International Conference on Electrical, Computer, and Energy Technologies (ICECET), Rome, Italy, 2026.