Introduction to Artificial Intelligence
Expert-defined terms from the Professional Certificate in Artificial Intelligence for Quality Management Pioneers course at London School of Planning and Management. Free to read, free to share, paired with a globally recognised certification pathway.
Artificial Intelligence (AI) #
Artificial Intelligence is a branch of computer science that focuses on creating… #
AI systems can learn from data, adapt to new inputs, and perform tasks such as image recognition, speech recognition, decision-making, and language translation. AI can be categorized into two types: Narrow AI, which is designed for a specific task, and General AI, which aims to replicate human intelligence across a wide range of tasks.
Algorithm #
An algorithm is a set of rules or instructions designed to solve a specific prob… #
In the context of AI, algorithms are used to process data, learn patterns, make predictions, and optimize decision-making processes. Common AI algorithms include machine learning algorithms like neural networks, decision trees, and support vector machines.
Backpropagation #
Backpropagation is an algorithm used in neural networks to train the model by ad… #
During backpropagation, the model calculates the error between the predicted output and the actual output and adjusts the weights to minimize this error. This process is repeated iteratively until the model converges to the desired level of accuracy.
Chatbot #
A chatbot is an AI #
powered software program designed to simulate conversation with human users. Chatbots can be used for a variety of purposes, such as customer service, information retrieval, and entertainment. They are typically powered by natural language processing (NLP) algorithms that enable them to understand and respond to user inputs in a conversational manner.
Deep Learning #
Deep learning is a subset of machine learning that focuses on training artificia… #
Deep learning models can automatically discover patterns, features, and relationships in complex datasets, making them well-suited for tasks such as image recognition, speech recognition, and natural language processing.
Expert System #
An expert system is an AI software program that emulates the decision #
making ability of a human expert in a specific domain. Expert systems are built using knowledge bases, inference engines, and rule-based systems to provide expert-level advice, recommendations, and solutions to users. They are commonly used in fields like healthcare, finance, and engineering.
Feature Engineering #
Feature engineering is the process of selecting, extracting, and transforming re… #
By selecting the right features and creating new ones, feature engineering helps models learn more effectively and make better predictions. Common techniques in feature engineering include one-hot encoding, normalization, and dimensionality reduction.
Genetic Algorithm #
Genetic algorithms are optimization algorithms inspired by the process of natura… #
They work by evolving a population of potential solutions to a problem over multiple generations, using techniques such as selection, crossover, and mutation to find the best solution. Genetic algorithms are commonly used for optimization problems with large search spaces.
Heuristic #
A heuristic is a rule of thumb or a practical approach used to solve problems qu… #
In AI, heuristics are commonly used in search algorithms, constraint satisfaction problems, and optimization techniques to guide the search process towards promising solutions. Heuristics can be domain-specific or general-purpose.
Image Recognition #
Image recognition, also known as computer vision, is a subfield of AI that focus… #
Image recognition algorithms can identify objects, scenes, patterns, and text in images, enabling applications like facial recognition, object detection, and image classification. Convolutional neural networks (CNNs) are commonly used for image recognition tasks.
Knowledge Graph #
A knowledge graph is a structured representation of knowledge in a domain, consi… #
Knowledge graphs organize information in a graph-like structure, where nodes represent entities, edges represent relationships between entities, and properties represent attributes of entities. Knowledge graphs are used in various AI applications, such as semantic search, recommender systems, and question answering.
Machine Learning #
Machine learning is a subset of AI that focuses on developing algorithms and mod… #
Machine learning algorithms can be categorized into supervised learning, unsupervised learning, and reinforcement learning, depending on the type of training data and feedback provided to the model.
Natural Language Processing (NLP) #
Natural Language Processing is a branch of AI that focuses on enabling computers… #
NLP algorithms can analyze and process text data, extract meaning, and generate responses in natural language. Common NLP tasks include sentiment analysis, named entity recognition, machine translation, and text summarization.
Optimization #
Optimization is the process of finding the best solution or configuration that m… #
In AI, optimization algorithms are used to fine-tune model parameters, hyperparameters, and decision-making processes to improve performance. Common optimization techniques include gradient descent, evolutionary algorithms, and simulated annealing.
Predictive Analytics #
Predictive analytics is the practice of using data and statistical algorithms to… #
In the context of AI, predictive analytics involves building machine learning models that can analyze historical data, identify patterns, and make predictions about future events. Predictive analytics is widely used in fields like finance, marketing, and healthcare.
Quantum Computing #
Quantum computing is a cutting #
edge computing paradigm that leverages the principles of quantum mechanics to perform calculations at a speed and scale far beyond classical computers. Quantum computers use quantum bits (qubits) to encode and process information, enabling them to solve complex problems in optimization, cryptography, and machine learning. Quantum computing has the potential to revolutionize AI and other fields.
Reinforcement Learning #
Reinforcement learning is a machine learning paradigm that focuses on training a… #
In reinforcement learning, agents learn through trial and error by interacting with the environment, receiving feedback in the form of rewards or penalties, and adjusting their actions to achieve long-term goals. Reinforcement learning is used in applications like game playing, robotics, and autonomous driving.
Supervised Learning #
Supervised learning is a machine learning approach where the model is trained on… #
The goal of supervised learning is to learn a mapping between input features and output labels, enabling the model to make accurate predictions on unseen data. Common supervised learning algorithms include linear regression, logistic regression, and support vector machines.
Unsupervised Learning #
Unsupervised learning is a machine learning approach where the model is trained… #
The goal of unsupervised learning is to discover patterns, relationships, and structures in the data without explicit guidance. Common unsupervised learning algorithms include clustering, dimensionality reduction, and association rule mining.
Validation #
Validation is the process of evaluating the performance and generalization abili… #
Validation techniques help assess the model's accuracy, reliability, and robustness by measuring its performance on a separate validation dataset. Common validation methods include cross-validation, hold-out validation, and bootstrapping.
Weak AI #
Weak AI, also known as narrow AI, refers to AI systems that are designed for spe… #
Weak AI systems excel at performing well-defined tasks, such as speech recognition, image classification, and recommendation systems. They are limited to the tasks they are designed for and do not exhibit consciousness or self-awareness.