AI Basics
This is what AI stands for.
What is Artificial Intelligence?
This is the term for the output a machine learning model tries to predict.
What is a label?
This is the term for breaking text into individual words or phrases for analysis.
What is tokenization?
This is the term for the layers of nodes in a neural network.
What are hidden layers?
Siri and Alexa are examples of this type of AI.
What are virtual assistants?
This is the opposite of artificial intellligence.
What is natural intelligence?
This is the term for the data used to teach an AI model.
What is training data?
This is the term for a computer program that simulates human conversation.
What is a chatbot?
This is the term for the smallest unit in a neural network.
What is a neuron?
This is the term for a robot that looks and acts like a human.
What is an android?
This is the term for AI trained with labeled data.
What is supervised learning?
This is the term for learning where the AI receives rewards or penalties.
What is reinforcement learning?
This is the name of the test proposed by Alan Turing to evaluate machine intelligence.
What is the Turing Test?
This is the technique used to prevent overfitting by randomly disabling neurons.
What is dropout?
This is the term for AI that creates new content like images or text.
What is generative AI?
This is the term for the process of improving an AI model’s performance by adjusting its internal parameters.
What is optimization?
This is the term for applying knowledge learned in one task to a different task.
What is transfer learning?
This is the term for AI models that can explain their decisions in human-understandable terms.
What is explainable AI?
This is the term for the function that introduces non-linearity in neural networks.
What is an activation function?
This is the term for bias that occurs when training data reflects human prejudices
What is algorithmic bias?
This is the term for the theoretical limit of intelligence an AI could reach, potentially surpassing human capabilities in all domains.
What is superintelligence?
This is the term for the phenomenon where a model performs well on training data but poorly on new data.
What is overfitting?
This is the term for when an NLP model generates fluent text that is factually incorrect or misleading.
What is hallucination?
This is the algorithm used to adjust weights in a neural network during training.
What is backpropagation?
This is the term for the challenge of ensuring AI goals align with human values.
What is the alignment problem?