Sep 23, 2016 · In this paper, we propose two deep architectures which can be trained jointly on multiple related tasks. More specifically, we augment neural ...

We proposed a generic multi-task framework, in which different tasks can share information by an external memory and communicate by a reading/writing mechanism.

This paper proposes a multi-task learning architecture with four types of recurrent neural layers to fuse information across multiple related tasks and ...

Deep Multi-Task Learning with Shared Memory for Text Classification. EMNLP 2016 · Pengfei Liu, Xipeng Qiu, Xuanjing Huang · Edit social preview.

Sep 10, 2024 · Multitask learning has been proven to be effective to learn share knowledge across tasks to improve performance of natural language tasks such ...

May 29, 2024 · Multi-task learning revolutionises AI by training models to handle multiple tasks simultaneously, improving efficiency and performance.

With an adaptive shared memory, TLASM is able to learn the relatedness among tasks adaptively, based upon which it can dynamically vary degrees of parameter ...

Jun 11, 2018 · Results on three groups of discrete-time nonlinear control tasks show that our proposed model can availably improve the performance of task with ...

1) Goal: MPPS mainly focuses on training shared parameters and can be added to the NAS-based architecture, while most NAS works aim to search for the best ...

This paper develops a multimodal demand forecasting approach, which can learn and utilize information/knowledge from different public transit modes.