Events News Research CBS CBS Publications Bioinformatics
Staff Contact About Internal CBS CBS Other

hoWWWlite - neural network simulator




howlite is an artificial neural network simulator especially designed to handle symbol sequences. The input to the network takes the form of single letter symbol strings - typically representing amino acids or nucleotides in biological sequences - while symbols in the output represent categories assigned to each single input symbol. The output categories will most often symbolize structural or functional aspects of the monomers in the linear input sequence.

Before the neural network is created and run, howlite reads a number of run-time parameters from the table below. These parameters control the architecture of the neural network, many aspects of the training process, the number of sequences used for training and testing, file names for additional input and output produced by the program, and the complexity and detail of the output delivered by the program.

Click here for detailed instructions.



CUSTOMIZE YOUR RUN

Select the values of the run-time parameters and click on the 'Run' button below.
Click on the description of each parameter for more information.


Neural network architecture
NIALPH - number of letters in the input alphabet
NOALPH - number of letters in the output alphabet
NWSIZE - window size in letters
N2HID - number of units in the second layer

Input and output alphabets
LETIN - input alphabet - input categories
LETOUT - output alphabet - output categories

Learning and test parameters
ETA - learning rate
ICETA - separate learning rate for each category
LSTOP - maximal number of training sweeps
ITEST - tsest frequency
IVIRGN - randomly generated synapses
ISSEED - synaps initialisation seed

Learning and test samples
LEARNC - number of sequences in training file
(view the graph)
LSKIP - number of sequences to skip in training file
(view the graph)
TESTC - number of sequences in test file
(view the graph)
ITSKIP - number of sequences to skip in test file
(view the graph)

Output levels
ICPER - percentage output for every example
ICSEQ - sequence output for every example
IACTIV - single window output activities, test only

Input/output
Network to use
(leave this field empty if a new network is trained)
Data for testing
Data for learning

Create and run the network