Selective transfer of neural network task knowledge
Robert E. Mercer, Daniel L. Silver · 2000
Within the context of artificial neural networks (ANN), we explore the question: How can a learning system retain and use previously learned knowledge to facilitate future learning? The research objectives are to develop a theoretical model and test a prototype system which sequentially retains ANN task knowledge and selectively uses that knowledge to bias the learning of a new task in an efficient and effective manner. A theory of selective functional transfer is presented that requires a learning algorithm that employs a measure of task relatedness. ηMTL is introduced as a knowledge based inductive learning method that learns one or more secondary tasks within a back-propagation ANN as a source of inductive bias for a primary task. ηMTL employs a separate learning rate, ηk, for each secondary task output k. ηk varies as a function of a measure of relatedness, Rk, between the kth secondary task and the primary task of interest. Three categories of a priori measures of relatedness are developed for controlling inductive bias. The task rehearsal method (TRM) is introduced to address the issue of sequential retention and generation of learned task knowledge. The representations of successfully learned tasks are stored within a domain knowledge repository. Virtual training examples generated from domain knowledge are rehearsed as secondary tasks in parallel with each new task using either standard multiple task learning (MTL) or ηMTL. TRM using ηMTL is tested as a method of selective knowledge transfer and sequential learning on two synthetic domains and one medical diagnostic domain. Experiments show that the TRM provides an excellent method of retaining and generating accurate functional task knowledge. Hypotheses generated are compared statistically to single task learning and MTL hypotheses. We conclude that selective knowledge transfer with ηMTL develops more effective hypotheses but not necessarily with greater efficiency. The a priori measures of relatedness demonstrate significant value on certain domains of tasks but have difficulty scaling to large numbers of tasks. Several issues identified during the research indicate the importance of consolidating a representational form of domain knowledge.