Skip to Main Content

Strategic Business Insights (SBI) logo

Neural Networks

This Explorer technology area has been discontinued.

Explorer offers limited, short-term web access to this discontinued technology. If you would like access to these documents, please contact us to discuss pricing and details.

Archived Viewpoints


About Neural Networks

March 2004

"Rules-based, Boolean computing assumes that we know best how to solve a problem," according to Mike Lynch, CEO of Autonomy Systems. Lynch says that neural networks taught him to approach computing from a completely different perspective: "The problem tells you how to solve the problem. That's what the next generation of computing is going to be about: listening to the world."

Neural networks do not rely on ruled-based programming for their performance. Instead, neural networks use learning algorithms to "tune" outputs to inputs. The technology finds use in situations in which rules are not explicitly available, and in which "tuning" inputs to outputs is easier than analyzing the internal reasoning process. Although neural networks find use in diverse applications, from industrial process control to face recognition, many new applications attempt to manage the growing complexity of IT and communications networks, including the Internet. As these networks themselves become more complex, rule-based approaches to managing them become less effective. Moreover, as the world moves toward ubiquitous connectivity, businesses must deal with an ever-growing influx of data about electronic business transactions. Currently, data mining uses neural networks to analyze the large volumes of data in the data warehouses that support modern business. More and more neural-network applications will focus on managing, and leveraging, the data emerging from electronic transactions, with general movement toward autonomous applications.

Another demand factor that will drive the neural-network market forward is the arrival of genetic medicine and bioinformatics. The gene sequences that researchers have discovered in the Human Genome Project have turned the life-sciences industry into one of the most data-intensive fields in the world. Neural networks will see increasing use as tools to put genetic data to work.

Neural networks are also active in application areas such as speech recognition, credit scoring, machine vision, and security-information analysis. All these applications need to deal with large volumes of data and to understand complex relationships within the data. Increasingly neural networks find use alongside synergistic technologies such as genetic algorithms and fuzzy logic in larger software applications. Neural networks will become an increasingly common behind-the-scenes technology, helping business users and consumers use computers in situations too complex for conventional logic to handle.