Some results on convergent unlearning algorithm
نویسندگان
چکیده
In this paper we consider probabilities of different asymptotics of convergent unlearning algorithm for the Hopfield-type neural network (Plakhov & Semenov, 1994) treating the case of unbiased random patterns. We show also that failed unlearning results in total memory breakdown.
منابع مشابه
Superlinearly convergent exact penalty projected structured Hessian updating schemes for constrained nonlinear least squares: asymptotic analysis
We present a structured algorithm for solving constrained nonlinear least squares problems, and establish its local two-step Q-superlinear convergence. The approach is based on an adaptive structured scheme due to Mahdavi-Amiri and Bartels of the exact penalty method of Coleman and Conn for nonlinearly constrained optimization problems. The structured adaptation also makes use of the ideas of N...
متن کاملManaging Obsolete Knowledge: towards a Clarified and Contextualized conception of unlearning
Although the IS literature has acknowledged the importance of unlearning in the context of IT change, research on unlearning has been marginal. Prior IS studies have identified four dominant mechanisms of unlearning, which are: individual forgetting; questioning and criticizing; stop using; and discarding. These four mechanisms reveal that there is not a clear conceptualization of unlearning th...
متن کاملNeural networks : iterative unlearning algorithm converging to the projector rule matrix
The iterative unlearning algorithm for connectivity self~correction is proposent. No
متن کاملThe Margin Perceptron with Unlearning
We introduce into the classical Perceptron algorithm with margin a mechanism of unlearning which in the course of the regular update allows for a reduction of possible contributions from “very well classified” patterns to the weight vector. The resulting incremental classification algorithm, called Margin Perceptron with Unlearning (MPU), provably converges in a finite number of updates to any ...
متن کاملA Simple Unlearning Framework for Online Learning Under Concept Drifts
Real-world online learning applications often face data coming from changing target functions or distributions. Such changes, called the concept drift, degrade the performance of traditional online learning algorithms. Thus, many existing works focus on detecting concept drift based on statistical evidence. Other works use sliding window or similar mechanisms to select the data that closely ref...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
عنوان ژورنال:
دوره شماره
صفحات -
تاریخ انتشار 1995