|Appears in Collections:||Computing Science and Mathematics Journal Articles|
|Peer Review Status:||Refereed|
|Title:||Structure Discovery in Mixed Order Hyper Networks (Forthcoming)|
|Keywords:||High order neural networks|
|Citation:||Swingler K Structure Discovery in Mixed Order Hyper Networks (Forthcoming), Big Data Analytics [non valid], 1 (1).|
|Abstract:||Background Mixed Order Hyper Networks (MOHNs) are a type of neural network in which the interactions between inputs are modelled explicitly by weights that can connect any number of neurons. Such networks have a human readability that networks with hidden units lack. They can be used for regression, classification or as content addressable memories and have been shown to be useful as fitness function models in constraint satisfaction tasks. They are fast to train and, when their structure is fixed, do not suffer from local minima in the cost function during training. However, their main drawback is that the correct structure (which neurons to connect with weights) must be discovered from data and an exhaustive search is not possible for networks of over around 30 inputs. Results This paper presents an algorithm designed to discover a set of weights that satisfy the joint constraints of low training error and a parsimonious model. The combined structure discovery and weight learning process was found to be faster, more accurate and have less variance than training an MLP. Conclusions There are a number of advantages to using higher order weights rather than hidden units in a neural network but discovering the correct structure for those weights can be challenging. With the method proposed in this paper, the use of high order networks becomes tractable.|
|Rights:||This item has been embargoed for a period. During the embargo please use the Request a Copy feature at the foot of the Repository record to request a copy directly from the author. You can only request a copy if you wish to use this work for your own research or private study.|
|Affiliation:||Computing Science - CSM Dept|
|Structure_BDAWithFigs.pdf||308.92 kB||Adobe PDF||Under Embargo until 1/6/2018 Request a copy|
Note: If any of the files in this item are currently embargoed, you can request a copy directly from the author by clicking the padlock icon above. However, this facility is dependant on the depositor still being contactable at their original email address.
This item is protected by original copyright
Items in the Repository are protected by copyright, with all rights reserved, unless otherwise indicated.
If you believe that any material held in STORRE infringes copyright, please contact firstname.lastname@example.org providing details and we will remove the Work from public display in STORRE and investigate your claim.