Introduction to Artificial Intelligence
Expert-defined terms from the Professional Certificate in Artificial Intelligence for Sustainable Urban Design course at Greenwich School of Business and Finance. Free to read, free to share, paired with a globally recognised certification pathway.
Artificial Intelligence (AI) #
Artificial Intelligence (AI)
Artificial Intelligence (AI) refers to the simulation of human intelligence proc… #
These processes include learning (the acquisition of information and rules for using the information), reasoning (using rules to reach approximate or definite conclusions), and self-correction. AI applications include expert systems, natural language processing, speech recognition, and machine vision.
Algorithm #
Algorithm
An algorithm is a set of rules or instructions designed to perform a specific ta… #
In the context of Artificial Intelligence, algorithms are used to process data, make decisions, and solve problems. Common AI algorithms include decision trees, neural networks, and genetic algorithms.
Backpropagation #
Backpropagation
Backpropagation is a supervised learning algorithm commonly used in neural netwo… #
It involves adjusting the weights of the network to minimize the difference between the actual output and the desired output. Backpropagation is an essential component of training neural networks.
Chatbot #
Chatbot
A chatbot is a computer program that simulates human conversation through text o… #
Chatbots are commonly used for customer service, information retrieval, and entertainment. They can be designed using rule-based systems or machine learning algorithms.
Deep Learning #
Deep Learning
Deep learning is a subset of machine learning that uses artificial neural networ… #
Deep learning algorithms can automatically discover patterns and features in data without the need for explicit programming. Deep learning has been successful in areas such as image recognition, speech recognition, and natural language processing.
Expert System #
Expert System
An expert system is a computer program that emulates the decision #
making ability of a human expert in a specific domain. Expert systems use knowledge representation, inference engines, and a user interface to provide advice or solutions to users. Expert systems are commonly used in medical diagnosis, financial planning, and troubleshooting.
Genetic Algorithm #
Genetic Algorithm
A genetic algorithm is a type of optimization algorithm inspired by the process… #
Genetic algorithms use the principles of selection, crossover, and mutation to evolve a population of candidate solutions towards an optimal solution. Genetic algorithms are useful for solving complex optimization problems.
Heuristic #
Heuristic
A heuristic is a rule of thumb or a practical approach used to solve problems th… #
Heuristics are commonly used in AI to guide search algorithms, decision-making processes, and problem-solving strategies. Heuristics can help AI systems make efficient and effective decisions.
Image Recognition #
Image Recognition
Image recognition is a computer vision task that involves identifying objects, p… #
AI algorithms, such as convolutional neural networks, are used to analyze and classify visual data based on features and patterns. Image recognition has applications in security, healthcare, and autonomous vehicles.
Knowledge Representation #
Knowledge Representation
Knowledge representation is the process of structuring information in a way that… #
Common methods of knowledge representation include logic, semantic networks, and ontologies. Effective knowledge representation is essential for building intelligent systems.
Machine Learning #
Machine Learning
Machine learning is a subset of AI that focuses on the development of algorithms… #
Machine learning algorithms can be supervised, unsupervised, or reinforcement learning.
Natural Language Processing (NLP) #
Natural Language Processing (NLP)
Natural language processing (NLP) is a branch of AI that deals with the interact… #
NLP algorithms enable computers to understand, interpret, and generate human language in a way that is meaningful and useful. NLP has applications in machine translation, sentiment analysis, and chatbots.
Optimization #
Optimization
Optimization is the process of finding the best solution or set of solutions to… #
In the context of AI, optimization algorithms are used to improve the performance, efficiency, or accuracy of AI systems. Common optimization techniques include gradient descent, genetic algorithms, and simulated annealing.
Pattern Recognition #
Pattern Recognition
Pattern recognition is a branch of AI that focuses on the identification and cla… #
AI algorithms, such as neural networks and support vector machines, are used to discover regularities and relationships in data. Pattern recognition is used in image analysis, speech recognition, and anomaly detection.
Q #
Learning
Q-learning is a reinforcement learning algorithm used to train an agent to make… #
Q-learning involves learning a Q-value function that estimates the expected cumulative reward for taking a specific action in a given state. Q-learning is used in robotics, game playing, and optimization problems.
Reinforcement Learning #
Reinforcement Learning
Reinforcement learning is a type of machine learning that involves training agen… #
Reinforcement learning algorithms use a trial-and-error approach to learn optimal policies through exploration and exploitation. Reinforcement learning is used in robotics, gaming, and autonomous systems.
Supervised Learning #
Supervised Learning
Supervised learning is a machine learning technique where a model is trained on… #
The goal of supervised learning is to make accurate predictions on unseen data by generalizing from the training examples. Common supervised learning algorithms include linear regression, decision trees, and support vector machines.
Unsupervised Learning #
Unsupervised Learning
Unsupervised learning is a machine learning technique where a model is trained o… #
Unsupervised learning algorithms aim to group similar data points together or reduce the dimensionality of the data. Common unsupervised learning algorithms include clustering, dimensionality reduction, and association rule mining.
Virtual Assistant #
Virtual Assistant
A virtual assistant is a software application that can perform tasks or services… #
Virtual assistants use AI technologies, such as natural language processing and machine learning, to understand and respond to user requests. Popular virtual assistants include Siri, Alexa, and Google Assistant.
Weak AI #
Weak AI
Weak AI, also known as narrow AI, refers to AI systems that are designed for spe… #
Weak AI systems can perform well-defined tasks, such as speech recognition or image classification, but lack the ability to understand or learn from diverse tasks. Weak AI is prevalent in current AI applications.
eXplainable AI (XAI) #
eXplainable AI (XAI)
Explainable AI (XAI) is an emerging field in AI that focuses on making AI system… #
XAI techniques aim to explain the decisions and predictions made by AI models in a human-readable and interpretable way. XAI is important for building trust in AI systems and ensuring accountability.
Yield Optimization #
Yield Optimization
Yield optimization is the process of maximizing the revenue or profit generated… #
In the context of AI for sustainable urban design, yield optimization algorithms can be used to optimize land use, transportation systems, energy consumption, and resource allocation. Yield optimization is essential for achieving efficient and sustainable urban planning.
Zero #
shot Learning
Zero #
shot learning is a machine learning paradigm where a model can generalize to unseen classes or tasks without labeled training data. Zero-shot learning algorithms leverage semantic embeddings or knowledge transfer techniques to learn new concepts from a few examples or textual descriptions. Zero-shot learning is useful for adapting AI models to new domains or applications.