https://vcclab.org

Virtual Computational Chemistry Laboratory

Home
About
Partners
Software
Articles
Servers
Jobs
Web Services
How to cite?
Contact










Welcome to the Associative Neural Network (ASNN)

start the program

Java security issues: recently Java has dramatically increased security requirements to applets. Thus, please, follow instructions in this FAQ to correcly setup access to the software.
  •  ASNN explicitly corrects bias of neural network ensemble => improved prediction ability;
  •  Similarity in space of models makes possible to interpret the ASNN results => better modelling;
  •  New data are incorporated in the network without retraining its weights => fast and accurate extrapolation;
  •  The method is based on a significant neurophysiological background.
  • ASNN represents a combination of an ensemble of feed-forward neural networks and the k-nearest neighbour technique. This method uses the correlation between ensemble responses as a measure of distance amid the analysed cases for the nearest neighbour technique. This provides an improved prediction by the bias correction of the neural network ensemble. An associative neural network has a memory that can coincide with the training set. If new data becomes available, the network further improves its predictive ability and provides a reasonable approximation of the unknown function without a need to retrain the neural network ensemble. This feature of the method dramatically improves its predictive ability over traditional neural networks and k-nearest neighbour techniques. Another important feature of ASNN is the possibility to interpret neural network results by analysis of correlations between data cases in the space of models.

    A standalone version of our software is also available.The data input format is described here.  

    References
    1. Tetko, I. V. Associative neural network, Neural Processing Letters, 2002, 16, 187-199, article.

    2. Tetko, I. V. Neural network studies. 4. Introduction to associative neural networks, J. Chem. Inf. Comput. Sci., 2002, 42, 717-28, article.

    3. Tetko, I. V.; Tanchuk, V. Y. Application of associative neural networks for prediction of lipophilicity in ALOGPS 2.1 program, J. Chem. Inf. Comput. Sci., 2002, 42, 1136-45, article.

    4. Tetko, I. V. Associative Neural Network, CogPrints Archive, cog00001441, 2001, article.

    Acknowledgment This software was developed with partial financial support from INTAS and University of Lausanne.


    Copyright 2001 -- 2023 https://vcclab.org. All rights reserved.