Seonglae Cho
변환
Reasoning from observed, specific cases to specific cases
unlabeled training data도 그들이 가진 특성(ex. 데이터 간 연결 관계, 거리)을 활용해 새로운 prediction을 하는 것
사전에 명시적인 function parameter를 학습하지 않는다
Transduction (machine learning)
In logic, statistical inference, and supervised learning,
transduction or transductive inference is reasoning from
observed, specific (training) cases to specific (test) cases. In contrast,
induction is reasoning from observed training cases
to general rules, which are then applied to the test cases. The distinction is
most interesting in cases where the predictions of the transductive model are
not achievable by any inductive model. Note that this is caused by transductive
inference on different test sets producing mutually inconsistent predictions.
https://en.wikipedia.org/wiki/Transduction_(machine_learning)
transductive learning VS inductive learning
inductive learning은 우리가 알고 있는 supervised learning으로, 어떤 function parameter (ex. classifier)를 주어진 labled training data로 학습하는 것이다. transductive learning은 unlabeled training data도 그들이 가진 특성(ex. 데이터 간 연결 관계, 거리)을 활용해 새로운 prediction을 하는 것이다. 따라서 사전에 명시적인 function parameter를 학습하지 않는다. 위키피디아의 다음 예가 차이점을 잘 설명해준다. The inductive approach to solving this problem is to use the labeled points to train a supe..
https://redstarhong.tistory.com/88
