On approximate learning by multi-layered feedforward circuits
نویسندگان
چکیده
منابع مشابه
On Approximate Learning by Multi-layered Feedforward Circuits
We consider the problem of efficient approximate learning by multilayered feedforward circuits subject to two objective functions. First, we consider the objective to maximize the ratio of correctly classified points compared to the training set size (e.g., see [3, 5]). We show that for single hidden layer threshold circuits with n hidden nodes and varying input dimension, approximation of this...
متن کاملBehavior Acquisition by Multi-Layered Reinforcement Learning
This paper proposes multi-layered reinforcement learning by which the control structure can be decomposed into smaller transportable chunks and therefore previously learned knowledge can be applied to related tasks in a newly encountered situations. The modules in the lower networks are organized as experts to move into di erent categories of sensor output regions and to learn lower level behav...
متن کاملGenetic Programming And Multi-agent Layered Learning By Reinforcements
We present an adaptation of the standard genetic program (GP) to hierarchically decomposable, multi-agent learning problems. To break down a problem that requires cooperation of multiple agents, we use the team objective function to derive a simpler, intermediate objective function for pairs of cooperating agents. We apply GP to optimize first for the intermediate, then for the team objective f...
متن کاملOn the semi-supervised learning of multi-layered perceptrons
We present a novel approach for training a multi-layered perceptron (MLP) in a semi-supervised fashion. Our objective function, when optimized, balances training set accuracy with fidelity to a graph-based manifold over all points. Additionally, the objective favors smoothness via an entropy regularizer over classifier outputs as well as straightforward 2 regularization. Our approach also scale...
متن کاملApproximate Inference by Compilation to Arithmetic Circuits
Arithmetic circuits (ACs) exploit context-specific independence and determinism to allow exact inference even in networks with high treewidth. In this paper, we introduce the first ever approximate inference methods using ACs, for domains where exact inference remains intractable. We propose and evaluate a variety of techniques based on exact compilation, forward sampling, AC structure learning...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: Theoretical Computer Science
سال: 2005
ISSN: 0304-3975
DOI: 10.1016/j.tcs.2005.09.008