Synthetic Data – Artificially generated data used to train AI models when real-world data is scarce.
Test Data – Data used to evaluate the performance of an AI model.
Training Data – Data used to teach an AI model how to recognize patterns.
Transformers – A deep learning architecture used in NLP, enabling models like GPT and BERT.
Turing Test – A measure of AI’s ability to exhibit human-like intelligence in conversation.
Underfitting – When an ML model is too simple to capture the underlying patterns in data.
Unsupervised Learning - ML where models learn patterns from unlabeled data.
Variance – A model’s sensitivity to fluctuations in training data, leading to overfitting.
Zero-Shot Learning – AI models that can make predictions on tasks they haven't been trained for.