Reminder of the First Paper on Transfer Learning in Neural Networks, 1976

被引:139
作者
Bozinovski, Stevo [1 ]
机构
[1] South Carolina State Univ, Orangeburg, SC 29117 USA
来源
INFORMATICA-AN INTERNATIONAL JOURNAL OF COMPUTING AND INFORMATICS | 2020年 / 44卷 / 03期
关键词
transfer learning; neural networks; MODEL;
D O I
10.31449/inf.v44i3.2828
中图分类号
TP31 [计算机软件];
学科分类号
081202 ; 0835 ;
摘要
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 the pioneering 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.
引用
收藏
页码:291 / 302
页数:12
相关论文
共 31 条
  • [1] Agarwal A., 1992, INTELLIGENCE ENG SYS, V2, P239
  • [2] [Anonymous], 1969, Perceptrons
  • [3] [Anonymous], 1967, INTRO CYBERNETICS
  • [4] Baxter J., NIPS95 POST C WORKSH
  • [5] A REPRESENTATION THEOREM FOR LINEAR PATTERN CLASSIFIER TRAINING
    BOZINOVSKI, S
    [J]. IEEE TRANSACTIONS ON SYSTEMS MAN AND CYBERNETICS, 1985, 15 (01): : 159 - 161
  • [6] Bozinovski S, 1995, 95107 CMPSCI U MASS
  • [7] Bozinovski S., 1972, PERCEPTRONS TRAINING
  • [8] Bozinovski S., 1981, Teaching space: A representation concept for adaptive pattern classification
  • [9] Bozinovski S., 1985, AUTOMATIKA, V26, P137
  • [10] Bozinovski S., 1978, P C ETAN, V22