I am a professor of Computer Engineering at Koç University in Istanbul and the founding director of the Artificial Intelligence Laboratory. Previously I was at the MIT AI Lab and later co-founded Inquira, Inc. My research is in natural language processing and machine learning. For prospective students here are some research topics, papers, classes, blog posts and past students.
Koç Üniversitesi Bilgisayar Mühendisliği Bölümü'nde öğretim üyesiyim ve Yapay Zeka Laboratuarı'nın kurucu müdürüyüm. Bundan önce MIT Yapay Zeka Laboratuarı'nda çalıştım ve Inquira, Inc. şirketini kurdum. Araştırma konularım doğal dil işleme ve yapay öğrenmedir. İlgilenen öğrenciler için araştırma konuları, makaleler, verdiğim dersler, Türkçe yazılarım, ve mezunlarımız.

April 29, 2021

Ozan Arkan Can, Ph.D. 2021

Current position: Applied Scientist - Amazon Search - Berlin (Homepage, LinkedIn, Email)
PhD Thesis: Cognitively-Inspired Deep Learning Approaches for Grounded Language Learning. April 2021. (PDF, Presentation, Publications, Code).

Thesis Abstract:

Designing machines that can perceive the surrounding world and interacting with us using human language is one of the long-standing goals of artificial intelligence. Although tremendous progress has been made to model the linguistic meanings computationally, how to best integrate linguistic and perceptual processing in multi-modal tasks is a significant open problem. This thesis explores several cognitively-inspired neural architectures that consider the different aspects of the language’s role in cognition, visual perception, and task execution. Proposed models incorporate design choices motivated by cognitive science studies and are based on the common patterns in vision-language tasks.

We begin by presenting an encoder-decoder network with a novel channel-based perceptual attention mechanism and its application to the navigational instruction following task. The perceptual processing component of this architecture is designed to focus on individual objects and properties within the environment using the language priors while preserving the spatial relations. To benefit from the designed component, we also propose an improved agent-centric world representation to allow the model to reason over the perception spatially.

Next, we explore the usage of the Neural Module Networks approach in a real robotic system for the first time. Since collecting large-scale real world data is a labor-intensive and expensive work, the system learns the language grounding on simulated data and the perceptual representation separately to overcome the scarce data problem. However, because of the separate learning processes, inconsistencies arise between the user’s and robot’s world models. To overcome this, we propose a Bayesian learning approach that uses the implicit information in the instruction to update the perceptual belief to align what the user sees and what the robot perceives.

In both parts, we demonstrate systems that use the high-level effect of language on visual processing, which operates on high-level representations. In addition to this, in the last part, we investigate the effect of language on low-level visual processing. To this end, we condition one or both low-level and high-level visual processing branches of a backbone architecture on language using language filters and apply these models to the image segmentation from referring expression task. Experiments show that modulating both low-level and high-level visual processing with language significantly improves the language grounding performance.

Full post...

February 01, 2021

Programlama pratik yaparak öğrenilir: Kumbara Dergisi Röportaj

İş Bankası, Koç Üniversitesi işbirliğinde ülkemizin bilimsel ve akademik faaliyetlerine katkıda bulunmak amacıyla “Yapay Zekâ Uygulama ve Araştırma Merkezi” kurdu. Bu merkezle yapay zekâ alanında ileri düzeyde çalışmalar gerçekleştirilmesi amaçlanıyor. Kumbara Dergisi olarak, Koç Üniversitesi İş Bankası Yapay Zekâ Uygulama ve Araştırma Merkezi Direktörü Prof. Dr. Deniz Yuret’e yapay zekâ alanı ve Yapay Zekâ Uygulama ve Araştırma Merkezi hakkında sorular sorduk.

Tüm Röportaj

Full post...

December 29, 2020

Ulaş Sert, M.S. 2020

Contact info:
M.S Thesis: Training a Bridge Bidding Agent using Minimal Feature Engineering and Deep Reinforcement Learning, Koç University, Department of Computer Engineering. December 2020. (PDF, Presentation, Code).

Thesis Abstract:
The game of contract bridge, or just bridge, is a four-player imperfect information card game where two partnerships of two players compete against each other. It has two main phases: bidding and play. While the computer players have approached human-level performance two decades ago in the playing phase, bidding is still a very challenging problem. This makes bridge one of the last popular games where computers still lag behind the expert human-level performance. During bidding, players only know their own cards while participating in a public auction. Performing well in this phase requires the players to figure out how to communicate with their partners using the limited vocabulary of bids to decide on a joint contract. This communication is restricted by the strict ordering of legal bids and can be negatively interfered by bids made by the opponent partnership. In this thesis, we experiment with several novel architectures with minimal feature engineering and evaluate them by using supervised training over a data set of expert-level human games. After that, we further study different forms of deep reinforcement learning to refine the resulting model by simulated gameplay. Lastly, we propose an oracle evaluation metric that can measure the quality of any bidding sequence with respect to the game-theoretical optimum.

Full post...