Our neural network technology offers businesses the opportunity to
take stock of detailed historic data and help make predictions for the future.
For some years now, researchers around the world have been
investigating and perfecting Neural Networks for such diverse tasks
Financial and Insurance Risk Assessment and
Some credit rating companies use neural networks to assess
the risk rating of clients' customers. Similarly, insurers may
use the technology to determine
policy pricing for different categories of
Industrial Process Control.
Applications include furnace control and other processes where
traditional mathematical models using second order differential
come into play.
such as robotics, ABS
braking systems, washing machines....
Neural Networks excel in applications where varied
external events can be modelled on historic data. It is
unnecessary for the investigator to know anything about the solution of
the model in order to achieve good results. A good
understanding of the business, process or task is however fundamental.
The way that this is accomplished is by
selecting appropriate "events" in the historic data and using
that to train the neural network through several iterative
processes. This is usually difficult and very time
Neural Networks are literally a simulation of a primitive
brain - specialised exactly to your criteria.
The data does not have to match future events exactly, but given
the right training data the network should converge on good
results - often better than traditional mathematical models.
Neural networks may even achieve 100% accuracy within your
Once the Neural Network has been trained within
agreed criteria it is "frozen" and can be embedded in a
run-time application. The run-time application is very efficient
and may be compiled into process control or embedded
Our technology allows us to create run-time versions of trained
neural networks compiled in the C and C++ programming languages to
allow very fast execution and porting to embedded applications.
Our network training technology uses special
unpublished training algorithms based on previous research. We
train the networks on our own custom test-bed using C++
and SQL server in conjunction with our own in-house class libraries
including data caching enhancements. This allows us to work
efficiently with very large data sets and manipulate historic data,
as we feel appropriate to solve the task.
The data does not have to match future
events exactly, but given the right training set it is often possible to get excellent
results very quickly.
It is important to note that not all predictive
problems can be easily solved with this technology. The
consultative phase may take some time. It is important in training
to ensure that the network does not "memorise" every instance
of the training data. The final solution, if one exists
is often a compromise that gives results within your
criteria. Bear in mind however that this may be much better
than any existing mathematical model. However, not all
problems can be solved using these techniques.
A feasibility study is required to give us
indications of the likely success of the project.
“We’re here to develop solutions that
are right for your needs today and tomorrow”.