Site Content
artificial intelligence (ai)
artificial intelligence (ai)
artificial intelligence (ai)
The development of computer systems that can perform tasks typically requiring human intelligence, such as reasoning, learning, and problem-solving.
Machine Learning (ML)
artificial intelligence (ai)
artificial intelligence (ai)
A subset of AI that enables computers to learn from data without being explicitly programmed for each task. ML focuses on building systems that improve their performance based on experience.
DATA
artificial intelligence (ai)
ALGORITHM
The raw information (numbers, text, images, etc.) that AI and ML models use to learn and make predictions or decisions.
ALGORITHM
unsupervised learning
ALGORITHM
A set of rules or instructions that a computer follows to solve a problem or perform a calculation. In AI, algorithms drive the learning and decision-making processes.
supervised learning
unsupervised learning
unsupervised learning
A type of ML where models are trained on labeled data (input-output pairs), allowing the system to learn the relationship between input and the correct output.
unsupervised learning
unsupervised learning
unsupervised learning
A type of ML where models are trained on unlabeled data, and the system must find patterns, structures, or relationships in the data on its own.
neural network
natural language processing
deep learning (Dl)
A series of algorithms that mimic the workings of the human brain to recognize patterns and relationships in data. Neural networks are the backbone of deep learning.
deep learning (Dl)
natural language processing
deep learning (Dl)
A subset of ML involving neural networks with many layers (hence "deep") that can process vast amounts of data to perform complex tasks like image recognition, natural language processing, and more.
natural language processing
natural language processing
natural language processing
A field of AI focused on enabling machines to understand, interpret, and generate human language, enabling applications like chatbots, language translation, and sentiment analysis
training data
The dataset used to teach a machine learning model during the learning phase. This data helps the model learn patterns and make predictions.
model
In AI, a model is the mathematical representation of a real-world process that has been trained on data to make predictions or decisions based on new inputs.
overfitting
A scenario where a model learns the training data too well, capturing noise and irrelevant details, making it perform poorly on new, unseen data.
underfitting
The opposite of overfitting, underfitting happens when a model is too simple and fails to capture the underlying patterns in the training data.
bias
A tendency of a machine learning model to consistently make errors in one direction due to flaws in the training data, algorithms, or decision-making process, leading to skewed results.
accuracy
A metric used to measure how well a model performs by calculating the proportion of correct predictions out of the total predictions made.
precision
A metric that measures the accuracy of positive predictions, showing how many of the positive predictions made by a model were correct.
Recall
A metric that measures how well a model identifies all relevant instances in a dataset. It shows how many of the actual positive cases the model correctly predicted.
Classification
Customers have questions, you have answers. Display the most frequently asked questions, so everybody benefits.
reinforcement learning (RL)
A type of ML where an agent learns by interacting with its environment and receiving rewards or penalties based on its actions, improving its strategy over time.
Site Content
classification
A type of supervised learning task where the model predicts discrete labels or categories, such as identifying an email as spam or not spam.
regression
A supervised learning task where the model predicts continuous values, such as predicting house prices based on various features (e.g., size, location).
feature engineering
The process of selecting and transforming raw data into features that better represent the problem to the model, improving its ability to make accurate predictions.
cross-validation
A technique used to evaluate a model’s performance by splitting the data into training and testing sets multiple times to ensure it generalizes well to unseen data.
generative ai
A branch of AI that focuses on generating new content, such as text, images, or music, by learning from a dataset and producing outputs that resemble the original data.
explainable ai (xai)
A movement in AI research focused on making the decision-making process of AI systems more transparent and interpretable to humans, addressing concerns over black-box models.
edge ai
AI that is processed locally on devices ("the edge") rather than relying on centralized cloud-based servers, allowing for faster responses and reduced latency, often used in IoT applications.
transfer learning
A machine learning technique where a model developed for one task is reused as the starting point for a model on a different but related task, speeding up the learning process for new applications.
computer vision
A field of AI focused on enabling machines to interpret and make decisions based on visual data (images, videos), used in applications like facial recognition, object detection, and autonomous vehicles.
hyperparameters
Settings or configurations used to control the training process of a machine learning model (e.g., learning rate, number of layers in a neural network), which are set before training and affect performance.
anomaly detection
The process of identifying rare or unusual patterns in data that do not conform to expected behavior, often used for detecting fraud, defects, or outliers in various industries.
turing test
A test proposed by Alan Turing to determine a machine’s ability to exhibit intelligent behavior indistinguishable from that of a human. If a machine can pass the test, it is considered capable of "thinking."