home *** CD-ROM | disk | FTP | other *** search
- Path: sparky!uunet!zaphod.mps.ohio-state.edu!sample.eng.ohio-state.edu!purdue!yuma!csn!ale!todd
- From: zazula@pri.com
- Newsgroups: comp.sys.next.announce
- Subject: ARCHIVES: NeuralNetworkClasses are on Purdue archive site
- Keywords: Neural Network HashTable Back-Propagation Pinnacle PRI
- Message-ID: <1992Aug31.233229.26239@liveware.com>
- Date: 31 Aug 92 23:32:29 GMT
- Sender: todd@liveware.com
- Reply-To: zazula@pri.com
- Followup-To: poster
- Organization: Pinnacle Research, Inc.
- Lines: 34
- Approved: todd@liveware.com
-
- Hi -
-
- I have uploaded the file "NeuralNetworkClasses.tar.Z" to the cs.orst.edu and
- nova.cc.purdue.edu archive sites. It contains an updated version of the
- neural-net stuff I posted a while back. It has a few more example files as
- well as a variation of the Neuron object that uses a HashTable data-structure
- to store the connections - this seems to run faster for larger networks.
-
- >From the README:
-
- The classes contained are:
-
- Neuron Implements a number of different types of neurons
- Neuron-HT Same as above with HashTable data-structure
- BackPropEngine Implements a back-propagation network
-
- The Example files are:
-
- bptest - An example of using the BackPropEngine (BPE) to perform the identity
- function
-
- boltz - An example of using stochastic Neurons to implement a Boltzman machine.
- This example implements the XOR function
-
- hoptest - An example of a Hopfield associative-memory network
-
- weighted_matching - An neural-network solution to the weighted-matching problem
-
- Ralph
- ---
- Ralph Zazula
- Pinnacle Research, Inc.
- zazula@pri.com (NeXT Mail)
- (602)529-1135
-