RML's AIMLearning™ Technology  is at the heart of Discipulus™. It lets Discipulus conduct genetic programming in processor-specific machine-code. Machine code genetic programming is sixty to two-hundred times faster than other modeling tools.

To get a sense of how much faster this is, running Discipulus on a single computer is equivalent to running other machine learning software on about one hundred computers, operating in parallel, simultaneously. Viewed another way, for very complex problems, Discipulus may take part of a day on a desktop computer to generate a reasonable solution. But other tools  would be require months to do the same thing.

This enormous speed lets Discipulus conduct hundreds of runs in the time it would take other systems to do one or two runs. As a result, Discipulus produces consistently high-precision models and gives customers the assurance that the models are among the best possible results for that problem--and it does that first time out and with no need for user set parameters.

Download the following additional information:

Comparison of Discipulus with other Machine Learning Techniques on Real World Problems and other Success Stories

• White Paper--Comparison of Discipulus™ Linear Genetic Programming Software with Support Vector Machines, Classification Trees, Neural Networks and Human Experts

• Publication--Discipulus Produces Best-Known Result on Discrimination of Unexploded Ordnance

• White Paper--Discipulus generates unprecedented Unexploded Ordnance discrimination at F.E.Warren Air Force Base.

• Publication--Discipulus generates best-known models for Waste Elimination Process Control, Soil Stabilization Modeling & Remote Sensing

• Publication--Discipulus outperforms neural-networks in creating Incinerator plant process control models

• Pre-Publication--Discipulus classifies MicroArray Tumor data with 100% Accuracy

• Publication--Discipulus predicts future financial problems for companies from their current financial statements

How Discipulus Works

• Pre-publication--Discipulus outperforms neural nets, support-vector-machines, CART, TreeNet, and Random Forests in predicting future corporate bankruptcy from current financial statements

• Publication--Discipulus outperforms neural nets, support-vector-machines- CART, TreeNet and Random forests in classifying tumors from microarray data.

• Publication--Discipulus outperforms resiliant backprop neural nets and support vector machines in detecting computer network security breaches.

• White Paper--Discipulus™ Linear Genetic Programming Software: How It Works

• Publication: Efficient Evolution of Machine Code for CISC Architectures using Blocks and Homologous Crossover (A detailed technical discussion of linear-machine-code-based genetic-programming)

• Discipulus Owner's Manual (Professional, Engineering and Enterprise)

• Discipulus Owner's Manual (Lite Version)

• Discipulus Life Tutorial