On the Strength of Incremental Learning Authors: Steffen Lange and Gunter Grieser. Source: Lecture Notes in Artificial Intelligence Vol. 1720, 1999, 118 - 131. Abstract. This paper provides a systematic study of incremental learning from noise-free and from noisy data, thereby distinguishing between learning from only positive data and from both positive and negative data. Our study relies on the notion of noisy data introduced in [22]. The basic scenario, named iterative learning, is as follows. In every learning stage, an algorithmic learner takes as input one element of an information sequence for a target concept and its previously made hypothesis and outputs a new hypothesis. The sequence of hypotheses has to converge to a hypothesis describing the target concept correctly. We study the following refinements of this scenario. Bounded example-memory inference generalizes iterative inference by allowing an iterative learner to additionally store an a priori bounded number of carefully chosen data elements, while feedback learning generalizes it by allowing the iterative learner to additionally ask whether or not a particular data element did already appear in the data seen so far. For the case of learning from noise-free data, we show that, where both positive and negative data are available, restrictions on the accessibility of the input data do not limit the learning capabilities if and only if the relevant iterative learners are allowed to query the history of the learning process or to store at least one carefully selected data element. This insight nicely contrasts the fact that, in case only positive data are available, restrictions on the accessibility of the input data seriously affect the capabilities of all types of incremental learning (cf. [18]). For the case of learning from noisy data, we present characterizations of all kinds of incremental learning in terms being independent from learning theory. The relevant conditions are purely structural ones. Surprisingly, where learning from only noisy positive data and from both noisy positive and negative data, iterative learners are already exactly as powerful as unconstrained learning devices. ©Copyright 1999 Springer-Verlag