COMPEL Glossary / neural-network
Neural Network
An artificial neural network is a computing system loosely inspired by the human brain, consisting of layers of interconnected nodes (neurons) that process data by adjusting numerical weights during training.
What this means in practice
Data enters through an input layer, passes through hidden layers where transformations occur, and exits through an output layer as a prediction or classification. Despite the biological metaphor, neural networks are mathematical functions -- they do not 'think' in any biological sense. Their power lies in the ability to learn arbitrarily complex relationships given enough data and parameters. Understanding neural networks at a conceptual level helps transformation leaders evaluate vendor claims, assess technical feasibility of use cases, and make informed decisions about infrastructure investments.
Why it matters
Neural networks are the computational foundation of modern AI, powering everything from image recognition to language generation. For business leaders, understanding neural networks at a conceptual level is essential for evaluating vendor claims, assessing technical feasibility, and making informed infrastructure investment decisions. Misunderstanding these systems leads to unrealistic expectations or missed opportunities.
How COMPEL uses it
During Calibrate, the Technology pillar assessment evaluates the organization's infrastructure readiness for neural network workloads. The Model stage uses conceptual neural network understanding to assess use case feasibility and infrastructure requirements. COMPEL's certification curriculum builds progressive neural network literacy from Level 1 foundations through Level 3 architectural decision-making.
Related articles in the Body of Knowledge
Related Terms
Other glossary terms mentioned in this entry's definition and context.