CsMTL MLP For WEKA: Neural Network Learning with Inductive Transfer

We present context-sensitive Multiple Task Learning, or csMTL as a method of inductive transfer. It uses additional contextual inputs along with other input features when learning multiple tasks so as to improve predictive performance. We modified the WEKA machine learning suite to accept csMTL encoding multiple tasks examples and performed tests on three domains. The results are not as supportive as we expected, however they still demonstrate that inductive transfer with csMTL is beneficial.

• Type: Conference
• Year: 2010
• Where: FLAIRS
• Authors: Liangliang Tu, Benjamin Fowler, Daniel L. Silver
• Keywords: Artificial Intelligence, Context-sensitive Multiple Task, FLAIRS 2010, Inductive Transfer, Multiple Tasks