Introduction of modern computational intelligence methods (evolutionary algorithms, machine learning and related fields) and their application to solving of real problems. Basic knowledge of machine learning, neural networks and evolutionary algorithms is required.
Teach advanced methods combining evolutionary algorithms, neural networks, and other computational intelligence methods. Deepen the knowledge from the introductory courses on neural networks, machine learning, data mining and evolutionary algorithms. The seminar will be focused on working with real data and the cooperation of various methods while solving difficult problems from the areas of optimization, learning and modelling.
Models for Surrogate Modelling
- Gaussian Processes - https://en.wikipedia.org/wiki/Kriging, https://gaussianprocess.org/gpml/chapters/RW.pdf
- Kernel Density Estimation (base of TPE) - https://en.wikipedia.org/wiki/Kernel_density_estimation
- Tree-Structured Parzen Estimator - https://arxiv.org/pdf/2304.11127, https://proceedings.neurips.cc/paper_files/paper/2011/file/86e8f7ab32cfd12577bc2619bc635690-Paper.pdf
Adversarial Examples
- FGSM method - https://arxiv.org/abs/1412.6572
- One-Pixel Attack - https://arxiv.org/abs/1710.08864
- Attacking Object Detectors - https://www.youtube.com/watch?v=MIbFvK2S9g8
- Patch Attacks - https://arxiv.org/abs/1712.09665
- Attack on Self-Driving Vehicles - https://keenlab.tencent.com/en/whitepapers/Experimental_Security_Research_of_Tesla_Autopilot.pdf
Deep Style:
- https://arxiv.org/abs/1508.06576
- DeepDream blog https://research.googleblog.com/2015/06/inceptionism-going-deeper-into-neural.html
Fooling Neural Networks:
Neural Machine Translation:
Image Super-Resolution:
Deep reinforcement learning:
- https://storage.googleapis.com/deepmind-data/assets/papers/DeepMindNature14236Paper.pdf
- https://arxiv.org/abs/1509.06461
- https://arxiv.org/abs/1611.05397
- https://arxiv.org/abs/1602.01783
AlphaGO:
Generative Adversarial Networks
Model calibration