Berker Demirel

I am a PhD candidate at Causal Learning and Artificial Intelligence Lab, IST Austria supervised by Francesco Locatello. My research interests lie in the domains of domain generalization and out-of-distribution generalization, where statistical and information-theoretical interpretations of the models are emphasized.

Prior to beginning my PhD, I earned a master's degree from Sabanci University. During this time, I was a member of the VPA Lab and was under the supervision of Asst. Prof. Huseyin Ozkan and Asst. Prof. Erchan Aptoula. The primary focus of my master's studies was on group activity recognition and domain generalization.

In the summer of 2019, I completed a summer internship at Erasmus University Rotterdam.

Email  /  CV  /  GitHub  /  Google Scholar  /  Twitter

We propose an additive disentanglement of domain specific and domain invariant features for the domain generalization problem. Unlike prior work, we demonstrate the potential benefits of utilizing domain specific features along with domain invariant ones. Moreover, we introduce a new data augmentation technique to enhance the generalization capacity of the architecture, where samples from different domains are mixed within the latent space.

We show that Group Activity Recognition Problem can be formulated using Attention Pooling mechanism and can perform on par with the other state-of-the-art methods even with a single RGB frame. Moreover, we manually reannotated the flawed instances in the Volleyball Dataset, which is one of the widely used datasets in Group Activity Recognition.

We developed a ranking algorithm that uses metrics of degree 1/2/3, closeness centrality, clustering coefficient, and page rank to rank the nodes in a graph. Then, we applied greedy coloring to the graph using the ranking as a guide, which resulted in significantly better colorings. Furthermore, we tried to extend this idea using a model-free policy based reinforcement learning algorithm while parallelizing C++ backend using OpenMP.

I re-implemented Andrej Karpathy's nanoGPT. It is designed to be simpler and easier to update. Performance evaluation is performed on Tiny Shakespeare Dataset and results can be found in the repository.

I implemented Uniform Manifold Approximation and Projection (UMAP) algorithm in Python from scratch and performed experiments on MNIST and Load Digits datasets.

I implemented convolutional Generator-Discriminator based GAN using PyTorch, and performed experiments on MNIST, CIFAR-10 and Celeb-A datasets.

I implemented Expectation-Maximization algorithm for Gaussian Mixture Model using Matlab.

We implemented Direction-Optimized BFS using OpenMP and CUDA.

Website template credits to Jon Barron.