최동완 연구실

Research proposal that focuses on enabling neural networks to store and retrieve information in a manner similar to human memory. Develops novel algorithms for memory consolidation and retrieval in neural networks.

Developing novel algorithms for enabling neural networks to learn continually without experiencing catastrophic forgetting. Studies memory consolidation and interference mechanisms in the brain.

Focuses on developing intelligent systems that provide explanations for decisions and actions, and interact with humans naturally. Studies human cognition and communication mechanisms.

Reducing the size and computational complexity of trained neural networks while preserving performance. Important for deploying on resource-constrained devices like mobile phones and edge devices.

Distributed machine learning paradigm enabling multiple parties to collaboratively train shared models without sharing data. Focuses on improving performance, convergence, and robustness of federated learning algorithms.