activity
20022005
most citedL1 regularization is better than L2 for learning and predicting chaotic systems

1 citations · 2 across the 9 of their papers we have counts for

collaborators

9 papers

cs.LG2005

Selection in Scale-Free Small World

Zs. Palotai, Cs. Farkas, A. Lorincz

In this paper we compare the performance characteristics of our selection based learning algorithm for Web crawlers with the characteristics of the reinforcement learning algorithm…

cs.LG20041 cited

L1 regularization is better than L2 for learning and predicting chaotic systems

Z. Szabo, A. Lorincz

Emergent behaviors are in the focus of recent research interest. It is then of considerable importance to investigate what optimizations suit the learning and prediction of chaotic…

cs.AI2004

Applying Policy Iteration for Training Recurrent Neural Networks

I. Szita, A. Lorincz

Recurrent neural networks are often used for learning time-series data. Based on a few assumptions we model this learning task as a minimization problem of a nonlinear least-square…

q-bio.NC2004

Intelligent encoding and economical communication in the visual stream

Andras Lorincz

The theory of computational complexity is used to underpin a recent model of neocortical sensory processing. We argue that encoding into reconstruction networks is appealing for co…

cs.IR2003

Centralized reward system gives rise to fast and efficient work sharing for intelligent Internet agents lacking direct communication

Zsolt Palotai, Sandor Mandusitz, Andras Lorincz

WWW has a scale-free structure where novel information is often difficult to locate. Moreover, Intelligent agents easily get trapped in this structure. Here a novel method is put f…

cs.AI20031 cited

Kalman-filtering using local interactions

Barnabas Poczos, Andras Lorincz

There is a growing interest in using Kalman-filter models for brain modelling. In turn, it is of considerable importance to represent Kalman-filter in connectionist forms with loca…