Monthly Archives: October 2022

 Fractional Fourier Transform Meets Transformer Encoder

At the intersection of classical signal processing and machine learning, AykutKocLab has made a significant contribution by introducing an advanced and efficient transformer model (FrFNet) that utilizes the fractional Fourier transform (FrFT) to mix the tokens of the transformer. The FrFNet has been described in the paper “Fractional Fourier Transform Meets Transformer Encoder” published in […]

Read More

The effect of gender bias on hate speech detection

We show that Transformer-based language models outperform bag-of-words and deep learning models in gender identity-based hate speech detection for both English and Turkish. Second, we find that gender identity-based hate speech detection can be improved by removing the gender bias in neural embeddings since gender-biased words can have offensive or hateful implications. The paper can […]

Read More

UMRAM/ASBAM Fall 2022 Seminars: “Neuroergonomics: Towards Ubiquitous and Continuous Measurement of Brain Function during Everyday Life”

Assoc. Prof. Hasan Ayaz Derexel University University of Pennsylvania   Date/Time: Tuesday, October 25th, 5:00 pm Zoom Meeting ID: 912 6646 5546 (Passcode: 896970)   Abstract: The understanding of the brain functioning and its utilization for real world applications is the next frontier. Existing studies with traditional neuroimaging approaches have accumulated overwhelming knowledge but […]

Read More