Problem Scoping

Problem Scoping

Reason — Problem scoping is the initial phase in any AI project where the problem is defined and understood in depth, including defining objectives.

To analyse collected data to identify patterns and gain insights

Reason — The primary purpose of data exploration is to analyse collected data to identify patterns and gain new insights.

Memory usage

Reason — Common performance metrics used in the evaluation phase include accuracy, precision, recall, F1-score and mean squared error, depending on the problem type.

Modifying the model's parameters to maximise functionality

Reason — Hyper-parameter tuning involves modifying the model's parameters to maximise its functionality and performance.

Healthcare

Reason — Healthcare as a theme of AI projects focuses on improving healthcare services by aiding in medical diagnoses, treatment planning and patient care.

Consent

Reason — Consent means getting permission from people before collecting their data. They should know what data is being collected and why.

1. The Problem scoping phase is the initial step in the AI Project Cycle where the problem is clearly defined and understood.
2. Ensuring the quality and relevance of data collected during the Data acquisition phase is crucial for the performance of AI models.
3. Descriptive statistics are used in data exploration to summarise and characterise the main features of the data.
4. In data modelling, model training involves dividing data into training and testing sets.
5. During the evaluation phase, performance metrics like accuracy, precision and recall are used to assess the performance of AI models.
6. AI projects in the education theme can enhance learning experiences through personalised education and virtual teaching assistants.
7. The 4Ws Problem Canvas includes answering questions about Who, What, Where and Why to thoroughly understand and define a problem.
8. Feature engineering involves creating new variables from raw data to enhance the functionality of AI models.

Two phases in the AI Project Cycle:

1. Problem Scoping
2. Data Acquisition

Two examples of data acquisition techniques:

1. Databases
2. APIs

Two performance metrics used in model evaluation:

1. Accuracy
2. Precision

Two themes for AI projects:

1. Education
2. Healthcare

Two ethical considerations in data collection:

1. Privacy
2. Consent

Both A and R are true and R is the correct explanation of A.

Reason — Feature engineering is part of data exploration, and it involves creating new variables or features from raw data to enhance the functionality of AI models.

(a) The primary goal of the data acquisition phase is to obtain the information needed for the AI project, ensuring that the data collected is relevant and of high quality for training and testing the AI models.

(b) Medical databases and health records

(c) Random Forest

(d) Obtaining informed consent from users

Machine learning is a part of Artificial Intelligence that involves training models using data so that they can learn patterns and make predictions or decisions without being explicitly programmed.

Analysing collected data to identify patterns and gain new insights is called data exploration. This stage includes descriptive statistics to enumerate and characterise the primary characteristics of the information using measures like mean, median, mode and standard deviation, visualisation to identify patterns, trends and outliers through graphical representations, data cleaning to handle missing values, duplicates and inconsistencies, and feature engineering to create new variables or features from raw data to enhance the functionality of AI models.

Feature engineering is the process of creating new variables or features from the raw data to enhance the functionality of AI models. This may include transforming, combining or generating new variables to improve model performance.

Problem scoping is the initial phase in any AI project where the problem is defined and understood in depth. This phase involves clearly articulating the problem, establishing clear, specific and measurable objectives, identifying all stakeholders involved or affected by the project, understanding their needs and expectations, and determining any constraints or limitations such as budget, time, technology or ethical considerations that may affect the project.

Hyper-parameter tuning involves modifying the models parameters to maximise their functionality. Techniques such as grid search and random search may be used to achieve this.

Performance metrics are used during the evaluation phase to assess how well the AI models solve the defined problem. Common performance metrics include accuracy, precision, recall, F1-score and mean squared error, depending on the problem type.

The primary goal of the problem scoping phase is to clearly define and understand the problem in depth, establish clear and specific objectives, identify stakeholders involved or affected by the project, and determine any constraints or limitations that may affect the AI project.

The purpose of feature engineering in AI projects is to create new variables or features from raw data to enhance the functionality of AI models.

The role of model validation in the AI Project Cycle is to evaluate the model's performance and generalisability by validating it against the testing set. This helps ensure that the model will perform well on new, unseen data.

Two techniques used in data acquisition are:

1. Databases
2. APIs

The objective of the data exploration phase in an AI project is to analyse collected data to identify patterns and gain new insights.

Two themes for AI projects:

1. Education – Virtual Teaching: AI that supports students by answering their questions and explaining difficult concepts.

2. Healthcare – Diagnostic Machines: AI that examines medical images or patient information to assist doctors in diagnosing diseases.

The significance of stakeholder identification in an AI project is to ensure that the project meets everyone's needs and expectations by identifying all the people or groups who are involved in, influence, or are affected by the project and understanding their roles and interactions with the AI system.

Hyper-parameter tuning in data modelling involves modifying the model's parameters to maximise its functionality and performance.