What is Underfitting?
When an AI model is too simple to capture the patterns in the data and performs poorly on everything.
Why It Matters
Underfitting means your model has not learned enough and needs more complexity or better training data.
Real-World Example
Trying to predict house prices using only the number of bedrooms when location and size also matter.
“Understanding terms like Underfitting matters because it helps you have better conversations with developers and make smarter decisions about your software. You do not need to be technical. You just need to know enough to ask the right questions.”
Related Terms
Overfitting
When an AI model memorises its training data too closely and performs poorly on new, unseen data.
Training Data
The dataset used to teach an AI model patterns and knowledge during its initial training.
Model Evaluation
The process of measuring how well an AI model performs on tasks it was designed for.
Hyperparameters
Settings you choose before training an AI model that control how the training process works.
Learn More at buildDay Melbourne
Want to understand these concepts hands-on? Join our one-day workshop and build a real web application from scratch.
Related Terms
Training Data
The dataset used to teach an AI model patterns and knowledge during its initial training.
Model Evaluation
The process of measuring how well an AI model performs on tasks it was designed for.
Overfitting
When an AI model memorises its training data too closely and performs poorly on new, unseen data.
Hyperparameters
Settings you choose before training an AI model that control how the training process works.
Large Language Model (LLM)
An AI system trained on massive amounts of text that can understand and generate human language.
Transformer
A type of AI architecture that processes text by paying attention to relationships between all words at once, rather...