The Waterfall approach is a sequential design process in which each phase of development must be completed before the next phase can begin. This means that once a phase is complete, it is difficult to go back and make changes, as any changes made to the project could potentially affect all the other phases. As a result, the Waterfall approach can make it difficult to adapt to changing customer requirements or adjust to new technology. This can ultimately lead to the failed delivery of an AI project.

References: [1] BCS Foundation Certificate In Artificial Intelligence Study Guide, Page number 19 [2] APMG International, “What is a Waterfall Model?”,  https://apmg-international.com/en/blog/what-is-a-waterfall-model/  [3] EXIN, “What is the Waterfall Model?”,  https://www.exin.com/blog/what-is-the-waterfall-model/

Online learning is a type of machine learning that can be used when a large dataset is limited in computational resources or if the data is frequently changing. It allows the system to learn from new data as it is being presented, rather than having to re-train the entire dataset each time new data is added. This makes it more efficient and effective than batch learning, as it only needs to process the new data and not the entire dataset. Online learning is often used in applications such as fraud detection, where new data is constantly being added and needs to be analyzed quickly.

For more information, please refer to the BCS Foundation Certificate In Artificial Intelligence Study Guide ( https://www.bcs.org/upload/pdf/bcs-foundation-certificate-in-artificial-intelligence-study-guide.pdf)  or the EXIN Artificial Intelligence Foundation Certification ( https://www.exin.com/en/exams/artificial-intelligence-foundation).

Activation Functions

An  activation function  in a neural network defines how the weighted sum of the input is transformed into an output from a node or nodes in a layer of the network.

https://machinelearningmastery.com/choose-an-activation-function-for-deep-learning/#:~:text=An%20activation%20function%20in%20a,a%20layer%20of%20the%20network .

An activation function is a mathematical function used in a neural network to determine the output of a neuron. Activation functions are used to transform the inputs into an output signal and can range from simple linear functions to complex non-linear functions. Activation functions are an important part of neural networks and help the network learn patterns and generalize data. Types of activation functions include sigmoid, ReLU, tanh, and softmax. References: BCS Foundation Certificate In Artificial Intelligence Study Guide,  https://bcs.org/certifications/foundation-certificates/artificial-intelligence/

In Machine Learning, the brain’s axons are referred to as nodes. Nodes are the components of a neural network that are responsible for processing the input data and generating the output. A node is a mathematical function that takes input data, performs a computation on it, and produces an output. Each node is connected to other nodes in the network via edges, which represent the strength of the connection between the respective nodes. The strength of the connection between two nodes is determined by the weights assigned to each edge. The weights are adjusted during the training process to generate the desired results.

For more information, please refer to the BCS Foundation Certificate In Artificial Intelligence Study Guide ( https://www.bcs.org/upload/pdf/bcs-foundation-certificate-in-artificial-intelligence-study-guide.pdf)  or the EXIN Artificial Intelligence Foundation Certification ( https://www.exin.com/en/exams/artificial-intelligence-foundation).

An intelligent robot uses Artificial Intelligence (AI) to perceive its environment, plan its actions and then act on them. This is sometimes referred to as the “sense, plan, act” cycle, and is at the heart of what makes a robot intelligent. By using AI, robots can sense their environment, plan their actions accordingly and then act on them in order to complete their tasks.

For more information, please refer to the BCS Foundation Certificate in Artificial Intelligence Study Guide:  https://www.bcs.org/category/18076/bcs-foundation-certificate-in-artificial-intelligence-study-guide.

Performance Measure of Agent  − It is the criteria, which determines how successful an agent is.

Behavior of Agent  − It is the action that agent performs after any given sequence of percepts.

Percept  − It is agent’s perceptual inputs at a given instance.

Percept Sequence  − It is the history of all that an agent has perceived till date.

Agent Function  − It is a map from the precept sequence to an action.

Agent Terminology

https://www.tutorialspoint.com/artificial_intelligence/artificial_intelligence_agents_and_environments.htm

An AI agent relies on its perceptual input, which is referred to as the agent's percept. This is the data that the agent collects through its sensors about its environment. The percept allows the agent to make decisions and take actions based on its environment. The agent's percept is important for Artificial Intelligence systems to be able to operate effectively. References:

[1] BCS Foundation Certificate In Artificial Intelligence Study Guide, "Reinforcement Learning", p.96-97. [2] APMG-International.com, "Foundations of Artificial Intelligence" [3] EXIN.com, "Foundations of Artificial Intelligence"

An intelligent robot is one that uses AI techniques, such as machine learning and natural language processing, to perceive, plan and act on its environment. Intelligent robots are able to process large amounts of data quickly and accurately, allowing them to make decisions and carry out tasks autonomously. Intelligent robots can be used in a variety of applications, from industrial automation to healthcare.