no code implementations • 25 Sep 2019 • Nguyen Anh Tuan, Hyewon Jeong, Eunho Yang, Sungju Hwang
To capture such dynamically changing asymmetric relationships between tasks and long-range temporal dependencies in time-series data, we propose a novel temporal asymmetric multi-task learning model, which learns to combine features from other tasks at diverse timesteps for the prediction of each task.
no code implementations • ICLR 2019 • Hyunwoo Jung, Moonsu Han, Minki Kang, Sungju Hwang
We tackle this problem by proposing a memory network fit for long-term lifelong learning scenario, which we refer to as Long-term Episodic Memory Networks (LEMN), that features a RNN-based retention agent that learns to replace less important memory entries based on the retention probability generated on each entry that is learned to identify data instances of generic importance relative to other memory entries, as well as its historical importance.