Abstract
This paper describes a work on transfer learning in neural networks carried out in 1970s and early 1980s, which produced its first publication in 1976. In the contemporary research on transfer learning there is a belief that pioneering work on transfer learning took place in early 1990s, and this paper updates that knowledge, pointing out that the transfer learning research started more than a decade earlier. This paper reviews that 1970s research and addresses important issues relevant for the current transfer learning research. It gives a mathematical model and geometric interpretation of transfer learning, and a measure of transfer learning indicating positive, negative, and no transfer learning. It presents experimental investigation in the mentioned types of transfer learning. And it gives an application of transfer learning in pattern recognition using datasets of images.
Highlights
Transfer learning is a machine learning method where a learning model developed for a first learning task is reused as the starting point for a learning model in a second learning task (Tan et al 2018)
The contribution of this paper is a review of an early period of transfer learning research, a period which was not known to the current researchers in transfer learning
In current history part of transfer learning, as covered by Wikipedia >Transfer Leaning >History (2020) there is information which suggests that the beginning of transfer learning research is in 1993
Summary
Transfer learning is a machine learning method where a learning model developed for a first learning task is reused as the starting point for a learning model in a second learning task (Tan et al 2018). Often previous learning is referred to as source and the learning as target (Pratt 1993, Pan and Yang 2010, Weiss et al 2016) It is using a pre-trained neural network (trained for Task1) for achieving shorter training time (positive transfer learning) in learning Task[2]. In the sequel the paper first reviews the neural network used in early research on transfer learning, during 1972-1981. It gives a mathematical model of supervised learning, in which it explicitly introduces transfer learning. It first shows experiments with small set of low resolution images representing letters, demonstrating experimentally the effect of tabula rasa, positive, and negative transfer.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have