Here is a list of terms provided by Google Gemini:
This glossary provides definitions for key terms commonly encountered in AI research. It's designed to be a starting point for your research and understanding, and further exploration of specific terms might be necessary depending on your needs.
General Terms:
- Artificial Intelligence (AI): The field of computer science concerned with creating intelligent machines capable of performing tasks that typically require human intelligence.
- Machine Learning: A subfield of AI where algorithms learn from data without being explicitly programmed.
- Deep Learning: A type of machine learning inspired by the structure and function of the brain, using artificial neural networks.
- Neural Network: An interconnected group of logical units that process data.
- Natural Language Processing (NLP): The field concerned with computers understanding and generating human language.
- Computer Vision: The field concerned with enabling computers to "see" and process visual information.
- Robotics: The field concerned with designing, building, and operating robots.
- Retrieval Augmented Generation: Use of a Large Language Model with the addition of external sources to generate context-specific answers.
Machine Learning Concepts:
- Algorithm: A set of instructions for solving a specific problem.
- Data: Information used to train and test machine learning models.
- Training Data: Data used to train a model to make predictions.
- Testing Data: Data used to evaluate the performance of a model on unseen data.
- Model: A representation of the learned knowledge used to make predictions.
- Prediction: An output of a model based on new input data.
- Overfitting: When a model performs well on training data but poorly on unseen data.
- Underfitting: When a model fails to capture the underlying patterns in the data.
Deep Learning Concepts:
- Neural Network: A series of interconnected nodes inspired by the structure of the brain.
- Activation function: A function applied to the output of each node in a neural network.
- Loss function: A function that measures the difference between the predicted output and the actual output.
- Optimization: The process of adjusting the parameters of a model to minimize the loss function.
- Backpropagation: An algorithm used to train neural networks by propagating the error back through the network.
Other Important Terms:
- AI Ethics: The study of the ethical implications of AI development and use.
- Bias: Unintended prejudice in a model that can lead to unfair outcomes.
- Explainability: The ability to understand how a model makes its decisions.
- Generative AI: AI systems that can create new content, such as text, images, or music.
- Reinforcement Learning: A type of machine learning where an agent learns through trial and error.
- Supervised Learning: Machine learning where the data is labeled with the desired output.
- Unsupervised Learning: Machine learning where the data is not labeled.