Explore tens of thousands of sets crafted by our community.
AI Terminology
30
Flashcards
0/30
Algorithm
A set of rules or steps for solving a problem or accomplishing a task.
Artificial Intelligence (AI)
The simulation of human intelligence processes by computer systems.
Machine Learning
A subset of AI that involves computers learning from data to improve their performance.
Deep Learning
A subset of machine learning consisting of neural networks with many layers.
Neural Network
A computational model designed to simulate the way the human brain processes information.
Supervised Learning
A type of machine learning where the model is trained on labeled data.
Unsupervised Learning
A type of machine learning where the model learns patterns in the data without being given explicit labels.
Reinforcement Learning
A type of machine learning where an agent learns to make decisions by taking actions in an environment to maximize some notion of reward.
Natural Language Processing (NLP)
A field of AI focused on enabling computers to understand, interpret, and generate human language.
Computer Vision
A field of AI that trains computers to interpret and understand visual information from the world.
Heuristic
A practical approach to problem-solving that employs a method not guaranteed to be perfect, but sufficient for reaching an immediate goal.
Expert System
A computer system emulating the decision-making ability of a human expert.
Backpropagation
A method used in artificial neural networks to calculate the error contribution of each neuron after a batch of data is processed.
Convolutional Neural Network (CNN)
A type of deep neural network used primarily to analyze visual imagery.
Generative Adversarial Network (GAN)
A model consisting of two neural networks, a generator and a discriminator, which compete against each other to generate new, synthetic instances of data.
Feature
An individual measurable property or characteristic of a phenomenon being observed.
Recurrent Neural Network (RNN)
A class of neural networks where connections between nodes form a directed graph along a temporal sequence, allowing it to exhibit temporal dynamic behavior.
Transfer Learning
A research problem in machine learning where a model developed for one task is reused as the starting point for a model on a second task.
Robotics
The branch of technology that deals with the design, construction, operation, and application of robots.
Semantic Analysis
The process of understanding the meaning and interpretation of words, signs, and sentence structure.
Gradient Descent
An optimization algorithm used to minimize a function by iteratively moving in the direction of steepest descent, as defined by the negative of the gradient.
Tensor
A multi-dimensional array used as a basic object in the data representations in neural networks.
Overfitting
A modeling error that occurs when a function is too closely fitted to a limited set of data points, resulting in poor predictive performance.
Underfitting
A modeling error which occurs when a function is not sufficiently complex relative to the structure of the data and cannot capture the underlying trend.
Bias
The error that is introduced by approximating a real-world problem by a simplified model.
Variance
The extent to which a model's predictions vary for a given dataset. High variance can cause an algorithm to model the random noise in the training data.
Precision
The ratio of correctly predicted positive observations to the total predicted positives in classification.
Recall
The ratio of correctly predicted positive observations to all actual positives in classification.
F1-Score
The weighted average of Precision and Recall, taking both false positives and false negatives into account. It is used in classification analysis.
Decision Tree
A predictive model that maps observations about an item to conclusions about the item's target value. It is a tree-like model of decisions.
© Hypatia.Tech. 2024 All rights reserved.
