Data-driven model validation for neutrino-nucleus cross section measurements

Autor: MicroBooNE collaboration, Abratenko, P., Alterkait, O., Aldana, D. Andrade, Arellano, L., Asaadi, J., Ashkenazi, A., Balasubramanian, S., Baller, B., Barnard, A., Barr, G., Barrow, D., Barrow, J., Basque, V., Bateman, J., Rodrigues, O. Benevides, Berkman, S., Bhanderi, A., Bhat, A., Bhattacharya, M., Bishai, M., Blake, A., Bogart, B., Bolton, T., Brunetti, M. B., Camilleri, L., Cao, Y., Caratelli, D., Cavanna, F., Cerati, G., Chappell, A., Chen, Y., Conrad, J. M., Convery, M., Cooper-Troendle, L., Crespo-Anadon, J. I., Cross, R., Del Tutto, M., Dennis, S. R., Detje, P., Diurba, R., Djurcic, Z., Duffy, K., Dytman, S., Eberly, B., Englezos, P., Ereditato, A., Evans, J. J., Fang, C., Fleming, B. T., Foreman, W., Franco, D., Furmanski, A. P., Gao, F., Garcia-Gamez, D., Gardiner, S., Ge, G., Gollapinni, S., Gramellini, E., Green, P., Greenlee, H., Gu, L., Gu, W., Guenette, R., Guzowski, P., Hagaman, L., Handley, M. D., Hen, O., Hilgenberg, C., Horton-Smith, G. A., Imani, Z., Irwin, B., Ismail, M. S., James, C., Ji, X., Jo, J. H., Johnson, R. A., Jwa, Y. J., Kalra, D., Karagiorgi, G., Ketchum, W., Kirby, M., Kobilarcik, T., Lane, N., Li, J. -Y., Li, Y., Lin, K., Littlejohn, B. R., Liu, L., Louis, W. C., Luo, X., Mahmud, T., Mariani, C., Marsden, D., Marshall, J., Martinez, N., Caicedo, D. A. Martinez, Martynenko, S., Mastbaum, A., Mawby, I., McConkey, N., Meddage, V., Mellet, L., Mendez, J., Micallef, J., Miller, K., Mistry, K., Mohayai, T., Mogan, A., Mooney, M., Moor, A. F., Moore, C. D., Lepin, L. Mora, Moudgalya, M. M., Babu, S. Mulleria, Naples, D., Navrer-Agasson, A., Nayak, N., Nebot-Guinot, M., Nguyen, C., Nowak, J., Oza, N., Palamara, O., Pallat, N., Paolone, V., Papadopoulou, A., Papavassiliou, V., Parkinson, H., Pate, S. F., Patel, N., Pavlovic, Z., Piasetzky, E., Pletcher, K., Pophale, I., Qian, X., Raaf, J. L., Radeka, V., Rafique, A., Reggiani-Guzzo, M., Ren, L., Rochester, L., Rondon, J. Rodriguez, Rosenberg, M., Ross-Lonergan, M., Safa, I., Schmitz, D. W., Schukraft, A., Seligman, W., Shaevitz, M. H., Sharankova, R., Shi, J., Snider, E. L., Soderberg, M., Soldner-Rembold, S., Spitz, J., Stancari, M., John, J. St., Strauss, T., Szelc, A. M., Taniuchi, N., Terao, K., Thorpe, C., Torbunov, D., Totani, D., Toups, M., Trettin, A., Tsai, Y. -T., Tyler, J., Uchida, M. A., Usher, T., Viren, B., Wang, J., Weber, M., Wei, H., White, A. J., Wolbers, S., Wongjirad, T., Wospakrik, M., Wresilo, K., Wu, W., Yandel, E., Yang, T., Yates, L. E., Yu, H. W., Zeller, G. P., Zennamo, J., Zhang, C.

Neutrino-nucleus cross section measurements are needed to improve interaction modeling to meet the precision needs of neutrino experiments in efforts to measure oscillation parameters and search for physics beyond the Standard Model. We review the di

Externí odkaz: http://arxiv.org/abs/2411.03280

Performance Evaluation of Deep Learning Models for Water Quality Index Prediction: A Comparative Study of LSTM, TCN, ANN, and MLP

Autor: Ismail, Muhammad, Abbas, Farkhanda, Shah, Shahid Munir, Aljawarneh, Mahmoud, Dhomeja, Lachhman Das, Abbas, Fazila, Shoaib, Muhammad, Alrefaei, Abdulwahed Fahad, Albeshr, Mohammed Fahad

Environmental monitoring and predictive modeling of the Water Quality Index (WQI) through the assessment of the water quality.
Comment: 18 pages

Externí odkaz: http://arxiv.org/abs/2411.01527

A Similarity-Based Oversampling Method for Multi-label Imbalanced Text Data

Autor: Karaman, Ismail Hakki, Koksal, Gulser, Eriskin, Levent, Salihoglu, Salih

In real-world applications, as data availability increases, obtaining labeled data for machine learning (ML) projects remains challenging due to the high costs and intensive efforts required for data annotation. Many ML projects, particularly those f

Externí odkaz: http://arxiv.org/abs/2411.01013

Homomorphism Counts as Structural Encodings for Graph Learning

Autor: Bao, Linus, Jin, Emily, Bronstein, Michael, Ceylan, İsmail İlkan, Lanzinger, Matthias

Graph Transformers are popular neural networks that extend the well-known Transformer architecture to the graph domain. These architectures operate by applying self-attention on graph nodes and incorporating graph structure through the use of positio

Externí odkaz: http://arxiv.org/abs/2410.18676

From Attention to Activation: Unravelling the Enigmas of Large Language Models

Autor: Kaul, Prannay, Ma, Chengcheng, Elezi, Ismail, Deng, Jiankang

We study two strange phenomena in auto-regressive Transformers: (1) the dominance of the first token in attention heads; (2) the occurrence of large outlier activations in the hidden states. We find that popular large language models, such as Llama a

Externí odkaz: http://arxiv.org/abs/2410.17174