[UAI] New book and software for neural networks and pattern recognition

From: IT NABNEY (i.t.nabney@aston.ac.uk)
Date: Wed Oct 31 2001 - 10:18:37 PST

  • Next message: Fabio Gagliardi Cozman: "[UAI] Summary: Generating Bayes nets randomly"

    BOOK AND SOFTWARE ANNOUNCEMENT
     
    A new release (3.2) of the Netlab toolbox is now available from
    http://www.ncrg.aston.ac.uk/netlab
     
    Written in Matlab, this freely available software includes implementations
    of a wide range of data analysis techniques, many of which are not
    available
    in other neural network simulation packages.
     
    An accompanying text book, titled "Netlab: Algorithms for Pattern
    Recognition"
    written by Ian Nabney is published by Springer (ISBN: 1-85233-440-1).
    This book has the following features:
     
    1. Supplies both algorithm knowledge and practical tools for a principled
    approach to application development.
     
    2. Brings together relevant theory with details of how to implement models
    efficiently and flexibly.
     
    3. Makes some of the leading edge research in this area accessible in a
    highly usable form.
     
    4. Provides researchers with a tool kit as a basis for developing new
    ideas.
     
    5. Worked examples and demonstration programs illustrate the theory and
    help
    the reader understand the algorithms and how to use them.
     
    The software includes the following algorithms:
     
    PCA
    Mixtures of probabilistic PCA
    Gaussian mixture model with EM training algorithm
    Linear and logistic regression with IRLS training algorithm
    Multi-layer perceptron with linear, logistic and softmax outputs and
    appropriate error functions
    Radial basis function (RBF) networks with both Gaussian and non-local basis
      functions
    Optimisers, including quasi-Newton methods, conjugate gradients and scaled
      conjugate gradients
    Multi-layer perceptron with Gaussian mixture outputs
      (mixture density networks)
    Gaussian prior distributions over parameters for the MLP, RBF and GLM
      including multiple hyper-parameters
    Laplace approximation framework for Bayesian inference (evidence procedure)
    Automatic Relevance Determination for input selection
    Markov chain Monte-Carlo including simple Metropolis and hybrid Monte-Carlo
    K-nearest neighbour classifier
    K-means clustering
    Generative Topographic Map
    Neuroscale topographic projection
    Gaussian Processes
    Hinton diagrams for network weights
    Self-organising map
                           

    -- 
    --------------------------------------------------------------------
    Dr. Ian Nabney				  i.t.nabney@aston.ac.uk
    Cardionetics Institute of Bioinformatics  tel: +44 (0)121 333 4631
    Aston University			  fax: +44 (0)121 333 4586
    Aston Triangle				
    Birmingham B4 7ET			  http://www.ncrg.aston.ac.uk/
    



    This archive was generated by hypermail 2b29 : Wed Oct 31 2001 - 10:24:52 PST