Abstracts of the Talks

Shimon Ullman- Atoms of Recognition and Top-down processing

The human visual system makes highly effective use of limited information: it can recognize not only objects, but also severely reduced sub-configurations in terms of size or resolution. The ability to recognize such minimal images is crucial for the interpretation of complex scenes, but is also challenging because recognition in this case depends on the effective use of all the available information. Our human and computer vision studies show that humans and existing models are very different in their ability to interpret minimal images. In particular, human vision combines bottom-up and top-down processing to achieve full interpretation of the object image. I will describe our studies and discuss implications to the representations used for recognition, brain mechanisms involved, and algorithms for the interpretation of complex scenes.

Suresh Manandhar- Challenges in Unsupervised Learning for NLP

In recent years, unsupervised learning is increasingly becoming an important topic within NLP. In this talk, I will summarise current progress in unsupervised learning focusing primarily on computational semantics and morphology. New developments in learning feature representations and concept learning provides a paradigm shift in NLP. However, despite these encouraging developments, significant challenges remain within each stage of the NLP pipeline – morphology, syntax and compositional distributional semantics. In addition to these, integration of deep learning with probabilistic knowledge representation languages provide additional challenges and avenues for further research.

Deniz Yüret- Learning to follow navigational instructions

In this talk we will explore the problem of teaching a computer to follow natural language instructions using examples of instruction-action pairs collected from humans in a maze like environment [1]. This problem is an example of grounded language learning, where the learning agent starts with no linguistic knowledge and has to infer the meanings of words, phrases, and sentences from example interactions. Recently, deep learning models for sequence-to-sequence mapping, originally developed for machine translation [2], were adapted for the grounded language learning problem [3]. Instead of translating a source language to a target language, grounded language learning can be seen as translating the instruction sequence to an action sequence mediated by perceptual information from the world. We will compare and evaluate alternative perceptual and attention systems for language learning in this simple setting.

[1] MacMahon, Matt, Brian Stankiewicz, and Benjamin Kuipers. "Walk the talk: Connecting language, knowledge, and action in route instructions." In Proceedings of the National Conference on Artificial Intelligence (AAAI). 2006.
[2] Sutskever, Ilya, Oriol Vinyals, and Quoc V. Le. "Sequence to sequence learning with neural networks." Advances in neural information processing systems. 2014.
[3] Mei, Hongyuan, Mohit Bansal, and Matthew R. Walter. "Listen, attend, and walk: Neural mapping of navigational instructions to action sequences." arXiv preprint arXiv:1506.04089 (2015).

Cem Bozşahin - Plans, Scripts, Discourse and Sentences

At the level of sentences, predicates bear thematic relations to their arguments, such as agent, patient, beneficiary. They show diversity in arity, from intransitives to ditransitives, and even more. At the level of discourse we do not see such diversity, or sensitivity to thematic roles. Recursion is also one observable difference between discourse and sentence structure.
The same differences appear to hold between plans, which are functions from states to states, and scripts, which are participant-taking functions with some likeness to thematic structure. We discuss a potential evolutionary basis for the similarity of the differences by pointing out a common computational mechanism.

Levent Akın - What Can AI and Robotics further Learn from Neuroscience?

In this talk, after a survey of the state-of-art in AI and robotics, some open problems and possible directions of research will be briefly reviewed. Some recent findings in neuroscience which may be of interest to the AI and robotics community and how they may help finding solutions to the open problems will be discussed.

Michelle Adams- Cognitive Aging And Its Relationship To Neuronal Structure And Function

Normal aging is accompanied by a range of biological changes that diminish quality of life. Understanding the changes contributing to memory decline is important for developing strategies to prevent or lessen cognitive problems. What are the specific changes that take place during aging which lead to decrements in neural function? What are the intrinsic biological determinants of those changes? What factors can ameliorate these changes? I will present data from the laboratory examining the neural consequences of aging on behavior and the brain. In addition, I will discuss the effects of an intervention, caloric restriction, which alters the course of neural aging.

List of Accepted Posters

Poster No

    1   Timothea Toulopoulou, Xiaowei Zhang and Daniel Weinberger. Polygenic risk profile score increases schizophrenia liability mostly through cognition pathways: Mathematical causation models with latent cognition and polygenic risk

    2   Oyku Ciftci, Gul Gunaydin, Emre Selcuk, Betul Urganci and Sumeyra Yalcintas. Language Style Matching during Face-To-Face Interactions: Preliminary Findings

    3   Özlem Ertan Kaya and Banu CangÖz. A stimulus set that can be used in neuroscience studies: Creating a photo set including faces with different levels of attractiveness

    4   Ozan Deniz, Kerem Alp Usal and Murat Perit Çakır. Connectionist Model for the Simon Task

    5   Aysun Kunduraci. Morphological Preforms and Nonterminal Categories

    6   Filiz Sayar. The Effects of The Contexts of Survival, Happiness and Death on Recall Performance

    7   Ece Kamer Takmaz, Emre Akbaş and Deniz Zeyrek. Turkish Language Models Utilizing Character- vs. Syllable-Based Recurrent Neural Networks

    8   Büşra Tanrıverdi Özkan and Sami Gulgoz. Interference in Autobiographical Memories

    9   Efe Cuma Yavuzsoy, Batuhan Uygar, Alp ÖzgÜn, Bora Garİpcan and Pınar Öz. Trans-zeatin riboside modulation of neurogenic astrocytes on primary cell culture from rat subventricular zone

    10   Derya Agis. Water, Bread, And Milk: A Cognitive Anthropological Approach To Sephardi Idioms And Proverbs

    11   Ahmet Üstün, Cem Bozşahin and Burcu Can. Learning to Map Words to Morphosemantics for Inflectional Morphologies

    12   Necva Bölücü and Burcu Can. Joint PoS Tagging and Stemming for Agglutinative Languages

    13   Elif Cemre Solmaz and Miri Besken. Perspective and Memory

    14   Doga Gulhan and Inci Ayhan. Short-term adaptation effects on perceived duration in random dot kinematograms (RDKs) and drifting gratings

    15   Didem Alashan, Doga Gulhan and Incı Ayhan. The Effect of Color Preference on the Perception of Emotionally Ambiguous Faces

    16   Babür Erdem, Kerem Alp Usal and Annette Hohenberger. Smell Recognition and Odor-Shape Matching

    17   Ece Kaya. Consonant deletion in Turkish

    18   Baris Serhan, Kerem Alp Usal and Annette Hohenberger. Difference between Tactile and Auditory Modalities in Time Perception

    19   Mustafa Seçkin, İlayda Demir, Mustafa Yasir Özdemir, Serdar Akkol and Hakan Gürvit. Early semantic impairment may be evident in the eye movements of patients with neurodegenerative disease.

    20   Benay Başkurt and Aaron Clarke. Neural Synchrony and Asynchrony as Mechanisms of Cortical Coding

    21   Özkan Kılıç, Cengiz Acartürk, Bilal Kırkıcı, Burcu Can and Ayşegül Özkan. The Role of Letter Frequency on Eye Movements in Turkish Pseudowords

    22   Ece Yallak, Ümit Akırmak, Elena Guerzoni and Esra Mungan. More Moses Illusion in Foreign Language Context

    23   Cengiz Acarturk, Bilal Kirkici, Özkan Kılıç, Aysegul Ozkan, Tugce Nur Bozkurt, Zuhal Ormanoglu and Aysel Yasemin Gol. The Investigation of Cognitive Processes in Reading: Development of a Corpus of Turkish Reading Patterns for Eye Movement Control Modeling

    24   Ece Kaya and Esra Mungan. In Search of Differential Enculturation and Entrainment Effects in Rhythmic Grouping

    25   Arvid Guterstam, Hugo Zeberg, Vedat Menderes Özçiftci and H. Henrik Ehrsson. The magnetic touch illusion: A perceptual correlate of visuo-tactile integration in peripersonal space

    26   Berhan Senyazar, Albert Ali Salah and Inci Ayhan. The Role of Attention on the Minimum Presentation Duration Required for Scene Recognition

    27   Murathan Kurfalı, Ahmet Üstün and Burcu Can. A Trie-Structured Bayesian Model for Unsupervised Morphological Segmentation

    28   Hatice K. Gökalp and Pınar Öz. The role of paraventricular thalamic nucleus and the orexinergic system in the prepulse inhibition network

    29   Selim Yilmaz and Ecir Kucuksille. Strengthed Bat Algorithm (SBA) for Training Feed-Forward Neural Network

    30   Dineshen Chuckravanen, Barkin Ilhan and Nizamettin Dalkilic. ROC and SATF analysis of grayscale test images (distractor L and target T) to customize a visual-search attention task for inducing mental fatigue

    31   Emre Aydogan and Sevil Sen. Automatic Generation of Mobile Malwares Using Genetic Programming

    32   Tzu-Ching Kao and Cem Bozsahin. Separable Words in Chinese Revisited

    33   Çağrı Şakiroğulları and H. Cem Bozşahin. Measuring Empirical Bias toward Ergativity and Accusativity

    34   Batuhan Uygar, Efe Cuma Yavuzsoy, Alp Özgün, Bora Garipcan and Pınar Öz. Agmatinergic modulation of neurogenic astrocytes on primary cell culture from rat subventricular zone

    35   Goksemin Fatma Sengul, Elif Tugce Karoglu, Zeynep Erbas, Ayse Gokce Keskus, Ergul Dilan Celebi, Melek Umay Tuz, Hatice Gunes Ozhan, Ayca Arslan Ergul, Fusun Doldur-Ballı, Ozlen Konu, Tayfun Ozcelik, Haluk Topaloglu and Michelle Maria Adams. The expression pattern of a three movement disorder-related genes throughout the lifespan of Zebrafish (Danio rerio)