Melih Kandemir

Search results

• 2022

  Evidential Turing Processes

  Kandemir, M., Akgül, A., Haussmann, M. & Unal, G., 2022, The Tenth International Conference on Learning Representations: ICLR 2022.

  Research output: Chapter in Book/Report/Conference proceeding › Article in proceedings › Research › peer-review

  File

  • Turing machines 100%
  • Uncertainty 90%
  • Deep learning 64%
  • Calibration 55%
  • Classifiers 50%
  2 Downloads (Pure)

• Learning Interacting Dynamical Systems with Latent Gaussian Process ODEs

  Yildiz, C., Kandemir, M. & Rakitsch, B., 2022, (Accepted/In press) Advances in Neural Information Processing Systems: NeurIPS. (Advances in Neural Information Processing Systems).

  Research output: Chapter in Book/Report/Conference proceeding › Article in proceedings › Research › peer-review

• Traversing Time with Multi-Resolution Gaussian Process State-Space Models

  Longi, K., Lindinger, J., Duennbier, O., Kandemir, M., Klami, A. & Rakitsch, B., 2022, 4th Annual Learning for Dynamics & Control Conference: L4DC.

  Research output: Chapter in Book/Report/Conference proceeding › Article in proceedings › Research › peer-review

  File

  • Differential equations 100%
  • Engines 71%
  • Experiments 39%
  4 Downloads (Pure)
• 2021

  Inferring the Structure of Ordinary Differential Equations

  Weilbach, J., Gerwinn, S., Weilbach, C. & Kandemir, M., 2021, ICML Time Series Workshop.

  Research output: Chapter in Book/Report/Conference proceeding › Article in proceedings › Research › peer-review

  File

  • Ordinary differential equations 100%
  • Dynamical systems 76%
  • Large scale systems 40%
  • Trajectories 32%
  4 Downloads (Pure)

• Learning Partially Known Stochastic Dynamics with Empirical PAC Bayes

  Haussmann, M., Gerwinn, S., Look, A., Rakitsch, B. & Kandemir, M., 2021, International Conference on Artificial Intelligence and Statistics: AISTATS. Vol. 130. (Proceedings of Machine Learning Research, Vol. 130).

  Research output: Chapter in Book/Report/Conference proceeding › Article in proceedings › Research › peer-review

  Open Access

  File

  • Differential equations 100%
  • Set theory 72%
  • Uncertainty 70%
  • Neural networks 68%
  • Experiments 39%
  5 Downloads (Pure)
• 2020

  Bayesian Evidential Deep Learning with PAC Regularization

  Haussmann, M., Gerwinn, S. & Kandemir, M., 2020, Advances in Approximate Bayesian Inference: AABI.

  Research output: Chapter in Book/Report/Conference proceeding › Article in proceedings › Research › peer-review

  File

  • Deep learning 100%
  • Uncertainty 70%
  • Neural networks 11%
  4 Downloads (Pure)
• 2019

  Deep Active Learning with Adaptive Acquisition

  Haussmann, M., Hamprecht, F. A. & Kandemir, M., 27. Jun 2019, International Joint Conference on Artificial Intelligence: IJCAI.

  Research output: Chapter in Book/Report/Conference proceeding › Article in proceedings › Research › peer-review

  File

  • Problem-Based Learning 100%
  • Labeling 42%
  • Reinforcement 17%
  • Machine learning 15%
  • Feedback 13%
  7 Downloads (Pure)

• Differential Bayesian Neural Nets

  Look, A. & Kandemir, M., 2019, NeurIPS Workshop on Bayesian Deep Learning.

  Research output: Chapter in Book/Report/Conference proceeding › Article in proceedings › Research › peer-review

  File

  • Ordinary differential equations 100%
  • Neural networks 56%
  • Learning systems 47%
  • Chemical activation 41%
  • Differential equations 41%
  6 Downloads (Pure)

• Sampling-Free Variational Inference of Bayesian Neural Networks by Variance Backpropagation

  Haussmann, M., Hamprecht, F. A. & Kandemir, M., 2019, Uncertainty in Artificial Intelligence: UAI.

  Research output: Chapter in Book/Report/Conference proceeding › Article in proceedings › Research › peer-review

  File

  • Backpropagation 100%
  • Sampling 74%
  • Neural networks 64%
  • Chemical activation 31%
  5 Downloads (Pure)
• 2018

  Evidential Deep Learning to Quantify Classification Uncertainty

  Sensoy, M., Kaplan, L. & Kandemir, M., 5. Jun 2018, Advances in Neural Information Processing Systems: NeurIPS. Vol. 2018-December. p. 3179-3189

  Research output: Chapter in Book/Report/Conference proceeding › Article in proceedings › Research › peer-review

  • Deep learning 100%
  • Uncertainty 70%
  • Neural networks 67%
  • Durability 18%
  • Machine learning 16%
  1 Downloads (Pure)
• 2017

  Prediction of active UE number with Bayesian neural networks for self-organizing LTE networks.

  Narmanlioglu, O., Zeydan, E., Kandemir, M. & Kranda, Y. T., 2017, Proceedings of the 2017 8th International Conference on the Network of the Future, NOF 2017: NOF. Mahmoodi, T., Secci, S., Cianfrani, A. & Idzikowaski, F. (eds.). p. 73-78

  Research output: Chapter in Book/Report/Conference proceeding › Article in proceedings › Research › peer-review

  • Long Term Evolution (LTE) 100%
  • Neural networks 53%
  • Feedforward neural networks 48%
  • Network management 23%
  • Heterogeneous networks 22%

• Variational Bayesian Multiple Instance Learning with Gaussian Processes.

  Haußmann, M., Hamprecht, F. A. & Kandemir, M., 2017, Proceedings - 30th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2017: CVPR. p. 810-819

  Research output: Chapter in Book/Report/Conference proceeding › Article in proceedings › Research › peer-review

  • Labels 100%
  • Volatile organic compounds 47%
  • Microarrays 44%
  • Object detection 40%
  • Tumors 40%
• 2016

  Gaussian Process Density Counting from Weak Supervision.

  Borstel, M. V., Kandemir, M., Schmidt, P., Rao, M. K., Rajamani, K. T. & Hamprecht, F. A., 2016, European Conference on Computer Vision: ECCV. Leibe, B., Matas, J., Sebe, N. & Welling, M. (eds.). p. 365-380

  Research output: Chapter in Book/Report/Conference proceeding › Article in proceedings › Research › peer-review

  • Blood 100%

• Variational Weakly Supervised Gaussian Processes.

  Kandemir, M., Haußmann, M., Diego, F., Rajamani, K. T., Laak, J. V. D. & Hamprecht, F. A., 2016, British Machine Vision Conference: BMVC.

  Research output: Chapter in Book/Report/Conference proceeding › Article in proceedings › Research › peer-review
• 2015

  Asymmetric Transfer Learning with Deep Gaussian Processes

  Kandemir, M., 2015, International Conference on Machine Learning: ICML. Bach, F. & Blei, D. (eds.). Vol. 37. p. 730-738

  Research output: Chapter in Book/Report/Conference proceeding › Article in proceedings › Research › peer-review

  • Transfer learning 100%
  • Tissue 71%
  • Tumors 43%

• Cell Event Detection in Phase-Contrast Microscopy Sequences from Few Annotations.

  Kandemir, M., Wojek, C. & Hamprecht, F. A., 2015, Medical Image Computing and Computer-Assisted Intervention – MICCAI 2015 - 18th International Conference, Proceedings: MICCAI. Frangi, A. F., Navab, N., Hornegger, J. & Wells, W. M. (eds.). p. 316-323

  Research output: Chapter in Book/Report/Conference proceeding › Article in proceedings › Research › peer-review

  • Microscopic examination 100%
  • Detectors 72%
  • Problem-Based Learning 21%
  • Classifiers 13%

• Detection of Retinopathy of Prematurity using multiple instance learning.

  Rani, P., Rajkumar, E. R., Rajamani, K. T., Kandemir, M. & Singh, D., 24. Sept 2015, 2015 International Conference on Advances in Computing, Communications and Informatics, ICACCI 2015: ICACCI. Mauri, J. L., Thampi, S. M., Wozniak, M., Marques, O., Krishnaswamy, D., Sahni, S., Callegari, C., Takagi, H., Bojkovic, Z. S., Vinod, M., Prasad, N. R., Alcaraz Calero, J. M., Rodrigues, J., Rodrigues, J., Que, X., Meghanathan, N., Sandhu, R. & Au, E. (eds.). p. 2233-2237

  Research output: Chapter in Book/Report/Conference proceeding › Article in proceedings › Research › peer-review

  • Labels 100%
  • Classifiers 83%
  • Digital cameras 65%
  • Screening 54%

• The Deep Feed-Forward Gaussian Process: An Effective Generalization to Covariance Priors.

  Kandemir, M. & Hamprecht, F. A., 2015, Proceedings in Machine Learning Research: PMLR. p. 145-159

  Research output: Chapter in Book/Report/Conference proceeding › Article in proceedings › Research › peer-review
• 2014

  Digital pathology: Multiple instance learning can detect Barrett's cancer.

  Kandemir, M., Feuchtinger, A., Walch, A. & Hamprecht, F. A., 29. Jul 2014, 2014 IEEE 11th International Symposium on Biomedical Imaging, ISBI 2014: ISBI. p. 1348-1351

  Research output: Chapter in Book/Report/Conference proceeding › Article in proceedings › Research › peer-review

  • Pathology 100%
  • Tissue 74%
  • Biopsy 57%
  • Logistic regression 48%
  • Benchmarking 45%

• Empowering Multiple Instance Histopathology Cancer Diagnosis by Cell Graphs

  Kandemir, M., Zhang, C. & Hamprecht, F. A., 2014, Medical Image Computing and Computer-Assisted Intervention, MICCAI 2014 - 17th International Conference, Proceedings: MICCAI. Springer, Vol. PART 2. p. 228-235 (Lecture Notes in Computer Science, Vol. 8674).

  Research output: Chapter in Book/Report/Conference proceeding › Article in proceedings › Research › peer-review

  • Tissue 100%
  • Microarrays 66%
  • Classifiers 41%

• Event Detection by Feature Unpredictability in Phase-Contrast Videos of Cell Cultures.

  Kandemir, M., Rubio, J. C., Schmidt, U., Wojek, C., Welbl, J., Ommer, B. & Hamprecht, F. A., 2014, Medical Image Computing and Computer Assisted Interventions: MICCAI. p. 154-161

  Research output: Chapter in Book/Report/Conference proceeding › Article in proceedings › Research › peer-review

  • Cell culture 100%
  • Cell death 57%
  • Stem cells 54%
  • Monitoring 43%
  • Bone 37%

• Instance Label Prediction by Dirichlet Process Multiple Instance Learning.

  Kandemir, M. & Hamprecht, F. A., 2014, Uncertainty in Artificial Intelligence - Proceedings of the 30th Conference, UAI 2014: UAI. Zhang, N. L. & Tian, J. (eds.). p. 380-389

  Research output: Chapter in Book/Report/Conference proceeding › Article in proceedings › Research › peer-review

  • Labels 100%

• Multiple Instance Learning with Response-Optimized Random Forests.

  Straehle, C. N., Kandemir, M., Köthe, U. & Hamprecht, F. A., 2014, International Conference on Pattern Recognition: ICPR. p. 3768-3773

  Research output: Chapter in Book/Report/Conference proceeding › Article in proceedings › Research › peer-review

  • Random forests 100%
  • Decision trees 45%
  • Learning algorithms 39%
  • Set theory 30%
  • Experiments 16%
• 2012

  Learning relevance from natural eye movements in pervasive interfaces

  Kandemir, M. & Kaski, S., 2012, International Conference on Multimodal Interfaces: ICMI. p. 85-92

  Research output: Chapter in Book/Report/Conference proceeding › Article in proceedings › Research › peer-review

• Unsupervised Inference of Auditory Attention from Biosensors.

  Kandemir, M., Klami, A., Vetek, A. & Kaski, S., 2012, European Conference on Machine Learning: ECML. p. 403-418

  Research output: Chapter in Book/Report/Conference proceeding › Article in proceedings › Research › peer-review
• 2011

  Multitask Learning Using Regularized Multiple Kernel Learning.

  Gönen, M., Kandemir, M. & Kaski, S., 2011, International Conference on Neural Information Processing: ICONIP. p. 500-509

  Research output: Chapter in Book/Report/Conference proceeding › Article in proceedings › Research › peer-review
• 2010

  Inferring object relevance from gaze in dynamic scenes.

  Kandemir, M., Saarinen, V-M. & Kaski, S., 2010, Eye Tracking Research and Applications: ETRA. p. 105-108

  Research output: Chapter in Book/Report/Conference proceeding › Article in proceedings › Research › peer-review