Перенос обучения (Transfer Learning) — это не просто современный тренд, а технология с историей, начавшейся еще в 1970-х годах. Исследование Загребского университета доказывает, что первые нейросети для распознавания текста и цифр использовали методы адаптации знаний задолго до бума современного ИИ.
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.