Computing:AI Flashcards
Describe the difference between ‘data-driven’ and ‘rule-based’ approaches to application development.
Data-driven approaches rely on analyzing large datasets to make decisions, while rule-based approaches use predetermined rules or algorithms to guide decision-making.
Name examples of AI applications.
Examples include virtual personal assistants (like Siri or Alexa), recommendation systems (like Netflix or Amazon), autonomous vehicles, and chatbots.
Outline some benefits and issues of using AI applications.
Benefits include increased efficiency, improved decision-making, and enhanced user experience. Issues may include privacy concerns, ethical considerations, and the potential for job displacement.
Define machine learning’s relationship to artificial intelligence.
Machine learning allows computers to perform tasks without explicit programming.
Name the three common approaches to machine learning -
Reinforcement learning, Supervised learning, and Unsupervised learning are the three common approaches to machine learning.
Describe how classification can be solved using supervised learning.
In supervised learning, classification tasks involve training a model on labeled data, where the model learns the relationship between input features.
Describe the impact of data on the accuracy of a machine learning (ML) model.
High-quality, relevant data can significantly improve the accuracy of an ML model, while low-quality or biased data can lead to inaccurate predictions and unreliable performance. (think about the apples and tomatoes – or the fish example)
Explain the need for both training and test data.
Training data is used to train an ML model, while test data is used to evaluate the model’s performance and assess its generalization to new, unseen data, ensuring that the model is not overfitting to the training data.
