Shift of bias for inductive concept learning

By Paul E. Utgoff. 1984

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Citations in the corpus

A Model of Inductive Bias Learning (2000, methodology): “7) “VBMS” or Variable Bias Management System was introduced as a mechanism for selecting amongst different learning algorithms when tackling a new learning problem. “STABB” or Shift To a Better Bias (Utgoff, 1986) was another early scheme for adjusting bias, but unlike VBMS, STABB was not primarily ”
Optimal Ordered Problem Solver (2002, neutral): “…at building a “General Problem Solver” —see also Rosenbloom et al. (1993)—much work has been done to develop mostly heuristic machine learning algorithms that solve new problems based on experience with previous problems, by incrementally shifting the inductive bias in the sense of Utgoﬀ (1986).”
Learning to Learn Using Gradient Descent (2001, methodology): “The use of previous learning experiences in inductive reasoning is known as “knowledge transfer” [4,1,14] or “inductive bias shifts” [ 15 ,6,12].”
Transfer Learning for Brain–Computer Interfaces: A Euclidean Space Data Alignment Approach (2018, background): “3) Concept shift [32]: the relationship between the inputs and the output changes.”
Transfer in Reinforcement Learning: A Framework and a Survey (2012, background): “On the other hand, taking inspiration from studies in psychology and neuroscience (Gentner et al, 2003; Gick and Holyoak, 1983), the transfer point of view, where learning tasks are assumed to be related and knowledge is retained and transferred, is considered as the most suitable perspective to des”
Separate-and-Conquer Rule Learning (1999, methodology): “In its original use (Utgoff 1986) the term bias shift referred to the process of automatically extending the representation language by constructing new features, a process that is commonly known as constructive induction (Matheus 1989).”
Model-based Adversarial Meta-Reinforcement Learning (2020, background): “The idea of learning to learn was established in a series of previous works (Utgoff, 1986; Schmidhuber, 1987; Thrun, 1996; Thrun & Pratt, 2012).”