17
2026-06Key Techniques: Graphic Models, Deep Generative Models, Variational Inference, Markov Chain Monte Carlo, Bayesian Neural Nets, Gaussian Processes, Bayesian Decision Making, Structure Learning. Applications: Generative Modeling, Semi-supervised Learning, Crowdsourcing, Anomaly Detection, Unvertainty in Deep Learning, Time-Series Modeling, Game, Reinforcement Learning, Healthcare.
17
2026-06Deep Neural networks (DNNs) are challenged by their vulnerability to adversarial examples, which are crafted by adding human-imperceptible noises to real examples, but make a model output inaccurate predictions. Researches on adversarial attacks and defenses are the foundations of building robust artificial intelligence systems.
17
2026-06Historically neuroscience has inspired many deep learning techniques. Now the two fields are converging. Neuroscience continues to inspire more powerful deep learning models and deep learning models are used to understand the working mechanism of the brain. Interaction between the two fields will benefit both of them.
17
2026-06Key Techniques: Knowledge Embedding, Information Routing Analysis, Knowledge Distillation, Network Pruning, Attribute Learning, Concept Learning, Visualization. Applications: Network Analysis, Adversarial Sample Detection, Visual Explanation, Knowledge Acquisition, Deep Learning Visualization.
17
2026-06Background: Reinforcement Learning enables the agent finishing several different tasks in unknown environments. Algorithmic Game Theory aims at finding good strategy for each agent in a multi-agent system under certain rules. Key Techniques: Conterfactual Regret Minimization, Thompson Sampling, Nash Equilibrium Finding, Model-based Reinforcement Learning, Combo Action.
17
2026-06Technology: Image/Video Understanding/Caption/Generation/Retrieval, Visual Question and Answer, Music Generation.