Zobrazeno 1 - 10
of 90
pro vyhledávání: '"Borisov, Vadim A."'
Understanding the complex interactions within the microbiome is crucial for developing effective diagnostic and therapeutic strategies. Traditional machine learning models often lack interpretability, which is essential for clinical and biological in
Externí odkaz:
http://arxiv.org/abs/2410.16109
Autor:
Borisov, Vadim, Schreiber, Richard H.
The tremendous success of chat-based AI systems like ChatGPT, Claude, and Gemini stems from Large Language Models (LLMs) trained on vast amount of datasets. However, acquiring high-quality, diverse, and ethically sourced training data remains a signi
Externí odkaz:
http://arxiv.org/abs/2407.14371
Autor:
Borisov, Vadim, Kasneci, Gjergji
The majority of existing post-hoc explanation approaches for machine learning models produce independent, per-variable feature attribution scores, ignoring a critical inherent characteristics of homogeneously structured data, such as visual or text d
Externí odkaz:
http://arxiv.org/abs/2212.12374
Tabular data is among the oldest and most ubiquitous forms of data. However, the generation of synthetic samples with the original data's characteristics remains a significant challenge for tabular data. While many generative models from the computer
Externí odkaz:
http://arxiv.org/abs/2210.06280
One of the core challenges facing the medical image computing community is fast and efficient data sample labeling. Obtaining fine-grained labels for segmentation is particularly demanding since it is expensive, time-consuming, and requires sophistic
Externí odkaz:
http://arxiv.org/abs/2208.03142
With a variety of local feature attribution methods being proposed in recent years, follow-up work suggested several evaluation strategies. To assess the attribution quality across different attribution techniques, the most popular among these evalua
Externí odkaz:
http://arxiv.org/abs/2202.00449
Understanding the results of deep neural networks is an essential step towards wider acceptance of deep learning algorithms. Many approaches address the issue of interpreting artificial neural networks, but often provide divergent explanations. Moreo
Externí odkaz:
http://arxiv.org/abs/2111.07379
Autor:
Borisov, Vadim, Leemann, Tobias, Seßler, Kathrin, Haug, Johannes, Pawelczyk, Martin, Kasneci, Gjergji
Heterogeneous tabular data are the most commonly used form of data and are essential for numerous critical and computationally demanding applications. On homogeneous data sets, deep neural networks have repeatedly shown excellent performance and have
Externí odkaz:
http://arxiv.org/abs/2110.01889
Autor:
Nikolaou, Nikolaos, Waldmann, Ingo P., Tsiaras, Angelos, Morvan, Mario, Edwards, Billy, Yip, Kai Hou, Tinetti, Giovanna, Sarkar, Subhajit, Dawson, James M., Borisov, Vadim, Kasneci, Gjergji, Petkovic, Matej, Stepisnik, Tomaz, Al-Ubaidi, Tarek, Bailey, Rachel Louise, Granitzer, Michael, Julka, Sahib, Kern, Roman, Ofner, Patrick, Wagner, Stefan, Heppe, Lukas, Bunse, Mirko, Morik, Katharina
The last decade has witnessed a rapid growth of the field of exoplanet discovery and characterisation. However, several big challenges remain, many of which could be addressed using machine learning methodology. For instance, the most prolific method
Externí odkaz:
http://arxiv.org/abs/2010.15996
Autor:
Borisov, Vadim A., Sidorchik, Irina A., Temerev, Victor L., Simunin, Mikhail M., Leont'eva, Natalya N., Muromtsev, Ivan V., Mikhlin, Yuri L., Voronin, Anton S., Fedorova, Zaliya A., Snytnikov, Pavel V., Shlyapin, Dmitry A.
Publikováno v:
In International Journal of Hydrogen Energy 12 July 2023 48(59):22453-22461
