Duyurular – Sayfa 5

Mayıs 6, 2024Wiener Filtering in Joint Time-Vertex Fractional Fourier Domains

We are excited to share our latest work on joint time-vertex signal processing published in IEEE Signal Processing Letters! In this paper, we explore the complexities of time-varying graph signals and how…

We are excited to share our latest work on joint time-vertex signal processing published in IEEE Signal Processing Letters! In this paper, we explore the complexities of time-varying graph signals and how they can be more efficiently processed using the joint time-vertex framework. Traditionally, separating signal from noise in these structures has posed significant challenges. However, our research introduces an innovative approach using the fractional Fourier domain, which has proven to achieve lower error rates compared to conventional methods. 🔍 Key Highlights:

We solve the optimal Wiener filtering problem within a new joint time-vertex fractional Fourier framework.
Our theoretical analysis and numerical experiments provide a novel perspective and demonstrate superior performance over existing filtering techniques.

The proposed method not only enhances our ability to handle time-varying graph signals but also opens up new possibilities for more sophisticated data analysis in network structures by using parametered transformations. #jointtimevertex #jtv #wiener #FourierTransform #FractionalFourierTransform #signalprocessing Paper: https://ieeexplore.ieee.org/document/10518099 Code: https://github.com/koc-lab/jfrt-optimal Abstract: Graph signal processing (GSP) uses network structures to analyze and manipulate interconnected signals. Graph signals can also be time-varying. The established joint time-vertex processing framework and corresponding joint time-vertex Fourier transform provide a basis to endeavor such time-varying graph signals. The optimal Wiener filtering problem has been deliberated within the joint time-vertex framework. However, the ordinary Fourier domain is only sometimes optimal for separating the signal and noise; one can achieve lower error rates in a fractional Fourier domain. In this paper, we solve the optimal Wiener filtering problem in the joint time-vertex fractional Fourier domains. We provide a theoretical analysis and numerical experiments with comprehensive comparisons to existing filtering approaches for time-varying graph signals to demonstrate the advantages of our approach.

Mart 22, 2024Graph Receptive Transformer Encoder for Text Classification

IEEE Transactions on Signal and Information Processing over Networks dergisinde yayınlanan "Graph Reseptive Transformer Encoder (GRTE) for Text Classification" başlıklı en son makalemizi paylaşmaktan mutluluk duyuyoruz! Yeni yaklaşımımız, metin sınıflandırması için dönüştürücülerin…

IEEE Transactions on Signal and Information Processing over Networks dergisinde yayınlanan “Graph Reseptive Transformer Encoder (GRTE) for Text Classification” başlıklı en son makalemizi paylaşmaktan mutluluk duyuyoruz! Yeni yaklaşımımız, metin sınıflandırması için dönüştürücülerin dikkat mekanizmalarındaki sınırlamaları ele almak amacıyla grafik sinir ağlarını (GNN’ler) büyük ölçekli önceden eğitilmiş modellerle birleştirir. GRTE, metinleri grafikler halinde temsil ederek küresel ve bağlamsal bilgileri alır, son teknoloji modellere kıyasla önemli performans iyileştirmeleri ve ~100 kata kadar hesaplama tasarrufu sunar. Daha fazla ayrıntı için makaleye göz atın! #NLP #TextClassification #Transformer #GNN #GRTE #TSIPN #IEEE Makale: https://ieeexplore.ieee.org/document/10477516 Kod: https://github.com/koc-lab/grte Özet: By employing attention mechanisms, transformers have made great improvements in nearly all NLP tasks, including text classification. However, the context of the transformer’s attention mechanism is limited to single sequences, and their fine-tuning stage can utilize only inductive learning. Focusing on broader contexts by representing texts as graphs, previous works have generalized transformer models to graph domains to employ attention mechanisms beyond single sequences. However, these approaches either require exhaustive pre-training stages, learn only transductively, or can learn inductively without utilizing pre-trained models. To address these problems simultaneously, we propose the Graph Receptive Transformer Encoder (GRTE), which combines graph neural networks (GNNs) with large-scale pre-trained models for text classification in both inductive and transductive fashions. By constructing heterogeneous and homogeneous graphs over given corpora and not requiring a pre-training stage, GRTE can utilize information from both large-scale pre-trained models and graph-structured relations. Our proposed method retrieves global and contextual information in documents and generates word embeddings as a by-product of inductive inference. We compared the proposed GRTE with a wide range of baseline models through comprehensive experiments. Compared to the state-of-the-art, we demonstrated that GRTE improves model performances and offers computational savings up to ~100x.

Mart 5, 2024Trainable Fractional Fourier Transform

IEEE Signal Processing Letters'da yayınlanan, makine öğrenimi ve sinyal işlemenin kesişimindeki yeni makalemize lütfen göz atın! We extend the theory of FrFT, a parametric signal transformation, by introducing it as a trainable…

Şubat 27, 2024Şizofrenide dilsel özelliklerin tanımlanmasında doğal dil işleme: Türkçe konuşanlardan bir örnek

UMRAM'da yapılan, Bilkent Üniversitesi Psikoloji ve Elektrik-Elektronik Mühendisliği Bölümleri ile Hacettepe Üniversitesi Psikiyatri Bölümü'nde şizofreniyi anlamaya yönelik NLP temelli yaklaşımlar üzerine ortak çalışmamız Schizophrenia Research'te yayımlandı! Bu çalışmada şizofrenide (SZ) Hint-Avrupa dili…

UMRAM’da yapılan, Bilkent Üniversitesi Psikoloji ve Elektrik-Elektronik Mühendisliği Bölümleri ile Hacettepe Üniversitesi Psikiyatri Bölümü’nde şizofreniyi anlamaya yönelik NLP temelli yaklaşımlar üzerine ortak çalışmamız Schizophrenia Research’te yayımlandı! Bu çalışmada şizofrenide (SZ) Hint-Avrupa dili olmayan Türkçenin dilsel özelliklerini tanımlamak için çoklu doğal dil işleme (NLP) yöntemlerini uygulayarak Türkçedeki NLP analiz sonuçlarının dilden bağımsız mı yoksa dilden bağımsız mı olduğunu gördük. dile bağımlı. Bulgularımız SZ’deki değişen dilsel özelliklerin çoğunlukla dilden bağımsız olduğunu gösterdi. Sonuçlarımız şizofrenide dil kalıplarını tanımlama konusunda ümit vericidir ve NLP ölçümlerinin dilsel özelliklerin hızlı ve objektif ölçümlerine izin verebileceğini göstermektedir. Makale: https://authors.elsevier.com/c/1if-S3HQGmiIHq Makale: https://www.sciencedirect.com/science/article/pii/S0920996424000628 Özet: Natural language processing (NLP) provides fast and accurate extraction of features related to the language of schizophrenia. We utilized NLP methods to test the hypothesis that schizophrenia is associated with altered linguistic features in Turkish, a non-Indo-European language, compared to controls. We also explored whether these possible altered linguistic features were language-dependent or -independent. We extracted and compared speech in schizophrenia (SZ, N = 38) and healthy well-matched control (HC, N = 38) participants using NLP. The analysis was conducted in two parts. In the first one, mean sentence length, total completed words, moving average type-token ratio to measure the lexical diversity, and first-person singular pronoun usage were calculated. In the second one, we used parts-of-speech tagging (POS) and Word2Vec in schizophrenia and control. We found that SZ had lower mean sentence length and moving average type-token ratio but higher use of first-person singular pronoun. All these significant results were correlated with the Thought and Language Disorder Scale score. The POS approach demonstrated that SZ used fewer coordinating conjunctions. Our methodology using Word2Vec detected that SZ had higher semantic similarity than HC and K-Means could differentiate between SZ and HC into two distinct groups with high accuracy, 86.84 %. Our findings showed that altered linguistic features in SZ are mostly language-independent. They are promising to describe language patterns in schizophrenia which proposes that NLP measurements may allow for rapid and objective measurements of linguistic features.

Şubat 12, 2024EE Mezunları Araştırma Konferansı’nda UMRAM öğrencilerine iki ödül

Elektrik Elektronik Mühendisliği (EE) Bölümü ve IEEE Öğrenci Kolu tarafından düzenlenen 34. Lisansüstü Araştırma Konferansı, 25 Ocak Perşembe günü EE binasının zemin katındaki amfilerde gerçekleşti. Bilkent EE yüksek lisans öğrencileri, gün boyu…

Elektrik Elektronik Mühendisliği (EE) Bölümü ve IEEE Öğrenci Kolu tarafından düzenlenen 34. Lisansüstü Araştırma Konferansı, 25 Ocak Perşembe günü EE binasının zemin katındaki amfilerde gerçekleşti. Bilkent EE yüksek lisans öğrencileri, gün boyu süren etkinlikte sözlü ve poster sunumlarıyla son teknoloji araştırma projelerini anlattılar. Bu yılın konferansı, üç zaman bloğunun her birinde eşzamanlı olarak gerçekleşen üç oturumla dokuz oturuma ayrılmış 38 sözlü sunumu içeriyordu. Sözlü oturumlarda lisansüstü öğrenciler araştırma projelerini paylaştılar ve izleyicilerden gelen soruları yanıtladılar. Yapay zeka ve makine öğrenimi, biyomedikal teknolojiler, iletişim ve ağ oluşturma, kontrol ve robotik, elektromanyetik, elektronik, entegre devreler ve sistemler, nanoteknoloji, optik ve fotonik ve sinyal işleme dahil olmak üzere çeşitli elektrik ve elektronik mühendisliği alanları kapsanmıştır. İki poster oturumu sırasında katılımcılar 25 sunum yapan kişiyle etkileşim kurma ve Enerji Verimliliği bölümündeki araştırmalar hakkında daha fazla bilgi edinme fırsatı buldu. Konferansta ayrıca EE lisans öğrencileri tarafından davet edilen bazı poster/demo sunumları da yer aldı. Etkinlik jürisi, sunumlar arasından “En İyi Sözlü Sunum” ödülüne üç sözlü sunum, “En İyi Poster Sunumu” ödülüne ise bir poster sunumu seçti. Sözlü bildiri ödülleri Hasan Atakan Bedel, Burak Çatalbaş ve Abdullah Erkam Arslan‘a verilirken, poster bildiri ödülünü Bilal Kabaş aldı. Konferansın başkanlığını Elektrik-Elektronik Mühendisliği Bölümü’nden Prof. Dr. Süleyman Serdar Kozat yaptı. Etkinliğin organizasyonunda EE yüksek lisans öğrencileri Ahmet Safa Öztürk, Issifu Iddrisu ve Ecem Şimşek ile IEEE Bilkent Öğrenci Kolu’ndan lisans öğrencileri Zeynep Naz Bayındır (EE/II) ve Baturalp Sönmez (CTIS/III) yer aldı. Etkinlik, bilgi paylaşımıyla dolu bir gün ve lisans öğrencilerine mühendislik ve bilim alanındaki araştırma dünyasını deneyimlemeleri için eşsiz bir fırsat sundu. Katılımcılar, diğer üniversitelerden araştırmacılar ve Türkiye’nin önde gelen mühendislik şirketlerinden profesyonellerle etkileşim kurma şansına sahip oldu.

Şubat 5, 2024Elginkan Vakfı 2023 Teknoloji Ödülü: Prof.Dr.Ergin Atalar

Elginkan Vakfı tarafından 2006 yılında hayata geçirilen “Elginkan Vakfı Türk Kültürü Araştırma ve Teknoloji Ödülleri”ni 18. Yılında alacaklar belli oldu. Türkiye’deki bilim, kültür ve sanat alanlarında yapılan çalışmalara, araştırmalara ve hizmetlere katkıda…

Aralık 29, 2023Automatic Construction of Sememe Knowledge Bases from Machine Readable Dictionaries

Check out our recent IEEE Transactions on Audio, Speech, and Language Processing article on automatic sememe knowledge base construction. Sememes are the smallest and indivisible semantic units of word meaning. A predefined…

Check out our recent IEEE Transactions on Audio, Speech, and Language Processing article on automatic sememe knowledge base construction. Sememes are the smallest and indivisible semantic units of word meaning. A predefined set of sememes is theoretically considered “the periodic table” of meaning in a natural language. However, unlike chemistry, the composition of the ultimate sememe set and optimal annotation of words with the elements of that set are open problems in language. Understanding semantics of language through the sememes is of fundamental importance to bolster the performance of a wide variety of high-level NLP applications, including today’s popular language models. Hence, linguistic experts are spending significant effort to manually determine this implicit and encompassing sememe set. In our article, we proposed the first automatic method for sememe set generation by using techniques like matrix factorization and topic modeling, utilizing tools such as Non-Negative Matrix Factorization (NMF), Latent Semantic Analysis (LSA), and Latent Dirichlet Allocation (LDA). The proposed method requires only a readily available dictionary and enhances the efficiency and scalability of generic sememe set construction. A fully computational and automatic way of devising sememe sets from readily available dictionaries can open up research directions and accelerate the existing ones where sememe knowledge is used to improve a wide range of high-level NLP tasks. Paper: https://ieeexplore.ieee.org/document/10375764 Code: https://github.com/koc-lab/mrd2skb Abstract: Sememes are the minimum semantic units of natural languages. Words annotated with sememes are organized into Sememe Knowledge Bases (SKBs). SKBs are successfully applied to various high-level language processing tasks as external knowledge bases. However, existing SKBs are manually or semi-manually constructed by linguistic experts over long periods, inhibiting their widespread utilization, updating, and expansion. To automatically construct an SKB from Machine-Readable Dictionaries (MRDs), which are readily available, we propose MRD2SKB as an automatic SKB generation approach. Well-established MRDs exist, and their construction is much simpler than SKBs. Therefore, the proposed MRD2SKB allows for fast, flexible, and extendable generation of SKBs. Building upon matrix factorization and topic modeling, we proposed several variants of MRD2SKB and constructed SKBs fully automatically. Both quantitative and qualitative results of extensive experiments are presented to demonstrate that the performances of the proposed automatically created SKBs are on par with manually and semi-manually prepared SKBs.

Aralık 8, 2023MRM article on Eddy Current Losses

Manoucher Takrimi authored an article on the eddy current losses in Magnetic Resonance in Medince. The article is visible in the offical web page. In this research, a novel method is introduced to enhance…

Kasım 21, 2023Quantitative radial force measurements of Woven EndoBridge devices

Dr. Algın ve ekibinin yeni deneysel çalışması yayınlandı. Prof. Dr. Oktay ALGIN’ın Gazi Üniversitesi ile son zamanlarda yaptıkları araştırma ‘Interventional Neuroradiology’ adlı uluslararası bilimsel dergide yayınlandı. Bu çalışmada, anevrizmaların tedavisininde kullanılan WEB…

Kasım 9, 2023RadGT: Graph and Transformer-Based Automotive Radar Point Cloud Segmentation

The work of Dr. Koç and his collaborators titled "RadGT: Graph and Transformer-based Automotive Radar Point Cloud Segmentation" has been published in IEEE Sensors Letters. In this study, we delve into the…

Kasım 9, 2023Measuring and Mitigating Gender Bias in Legal Contextualized Language Models

As the popularity and importance of large language models (LLMs) are soaring by the day, I am happy to announce that our recent work on gender bias and fairness in contextualized language…

As the popularity and importance of large language models (LLMs) are soaring by the day, I am happy to announce that our recent work on gender bias and fairness in contextualized language models for natural legal language processing (NNLP) is now out at ACM Transactions on Knowledge Discovery from Data! Computational law, mostly based on natural language processing (NLP) and machine learning, has recently gained significant interest due to the technological improvements, abundance of legal texts, and increasing demand from legal professionals for technology. Since law is probably one of the most influential areas that touch upon lives, fairness and bias-free algorithm development are even more critical when we talk about artificial intelligence in law practices. In our article titled “Measuring and Mitigating Gender Bias in Legal Contextualized Language Models”, we have introduced the first study on detecting and eliminating gender and societal bias issues present in contextualized large language models for legal NLP. This work brings the important issue of bias to the attention of computational law community, where the effects of law on people’s lives has doubled the need for studying bias. Paper: https://dl.acm.org/doi/10.1145/3628602 Code: https://github.com/koc-lab/ContextLegalBias Abstract: Transformer-based contextualized language models constitute the state-of-the-art in several natural language processing (NLP) tasks and applications. Despite their utility, contextualized models can contain human-like social biases as their training corpora generally consist of human-generated text. Evaluating and removing social biases in NLP models has been a major research endeavor. In parallel, NLP approaches in the legal domain, namely legal NLP or computational law, have also been increasing. Eliminating unwanted bias in legal NLP is crucial since the law has the utmost importance and effect on people. In this work, we focus on the gender bias encoded in BERT-based models. We propose a new template-based bias measurement method with a new bias evaluation corpus using crime words from the FBI database. This method quantifies the gender bias present in BERT-based models for legal applications. Furthermore, we propose a new fine-tuning-based debiasing method using the European Court of Human Rights (ECtHR) corpus to debias legal pre-trained models. We test the debiased models’ language understanding performance on the LexGLUE benchmark to confirm that the underlying semantic vector space is not perturbed during the debiasing process. Finally, we propose a bias penalty for the performance scores to emphasize the effect of gender bias on model performance.

Ekim 12, 2023MR Güvenlik – Kullanıcı Eğitimi