These AI Class 10 Notes Chapter 2 AI Project Cycle Class 10 Notes simplify complex AI concepts for easy understanding.
Class 10 AI Project Cycle Notes
Al Project Cycle Class 10 Notes
It is a step-by-step process that a person should follow to develop an AI Project to solve a problem. AI Project Cycle provides us with an appropriate framework which can lead us to achieve our goal.
The AI project cycle is a structured roadmap for developing and deploying artificial intelligence projects to solve real-world problems.
This systematic approach helps define objectives, collect relevant data, uncover hidden insights, create models for AI systems, and assess their performance.
Different Stages of AI Cycle
The AI project cycle mainly has 5 stages
- Problem Scoping – understanding the problem
- Data Acquisition – collecting accurate and reliable data
- Data Exploration – arranging the data uniformly
- Modelling – creating models from the data
- Evaluation – evaluating the project
Problem Scoping Class 10 Notes
Problem scoping is the process of identifying the scope the problem that need to be solved. Problem scoping is a critical initial phase in the AI project cycle where the focus is on defining the problem or opportunity that the AI solution aims to address. This stage sets the foundation for the entire project and significantly influences its success.
We use the 4 Ws Problem Canvas to understand the problem in a better way.
The 4Ws Problem Canvas
The 4 W problem canvas helps in identifying the key elements related to the problem.
The 4Ws are
- Who? This block helps in analysing the people who are getting affected directly or indirectly due to a problem. Under this, we find out who are the ‘Stakeholders’ to this problem?
- What? This block helps to determine the nature of the problem. Under this block, we also gather evidence to prove that the problem you have selected actually exists.
- Where? This block will help us to look into the situation in which the problem arises, and the locations.
- Why? In this block, we think about the benefits which the stakeholders would get from the solution and how it will benefit them as well as the society.
Problem Statement Template
The problem statement template takes the information gathered from the 4 Ws problem canvas (Who, What, When, Why) and Condenses it into a clear, concise statement. This process reffines a broad problem into a well-defined one, allowing you to focus your efforts on a specific issue and develop targeted solution.
Data Acquisition Class 10 Notes
Data Acquisition is the process of collecting the required data from reliable sources. This is the second phase of the AI project cycle, which is focused on obtaining the necessary data for the project. Data needs to be accurate and reliable.
For example, To make an Artificially Intelligent system which can predict the weather, you would feed the data of previous days for that locations into the machine. This is the data with which the machine can be trained.
Now, once it is ready, it will predict the weather conditions efficiently. The previous weather data here is known as “Training Data” while the next weather prediction data set is known as the “Testing Data”.
Data Features
Data features refer to the individual characteristics of a dataset that provide information for analysis. These attributes can be numerical, categorical, or textual. They serve as the input variables for machine learning models, influencing the model’s ability to make predictions or classifications based on patterns within the data.
Data Sources
Data source is where does one get data from? It’s essential to consider data quality, relevance, and ethical considerations when choosing and handling data from these sources. Some important ways to collect data are
Surveys Surveys involve gathering data by asking questions directly to individuals or groups of people.
Web Scraping Web scraping involves extracting data from websites and web pages.
Sensors Sensors are devices that collect data from the physical world and convert it into a form that computers can understand. For example, temperature sensors in weather stations measure the ambient temperature, and this data is used to predict weather conditions. In smartphones, accelerometers detect the phone’s movement and orientation, allowing for automatic screen rotation and activity tracking.
Cameras Cameras capture visual data in the form of images or videos. They can be used to collect data in fields such as surveillance, computer vision, image processing, and object recognition.
Observations Observations involve collecting data by monitoring or measuring phenomena. In agriculture, for example, farmers observe crop health using drones equipped with cameras. These drones take high-resolution images of fields, which are then analyzed to detect issues like pest infestations or water stress, helping farmers make better decisions about crop management.
API (Application Programming Interface) APIs (Application Programming Interfaces) are tools that allow different software applications to communicate and share data. For example, social media platforms like Twitter offer APIs that developers can use to access tweets and user interactions. Businesses use this data to analyze trends, monitor brand reputation, and engage with customers in real-time.
One of the most dependable and trustworthy sources for data is government-hosted open-access websites. Examples of such government portals include data.gov.in and india.gov.in.
Data Exploration Class 10 Notes
Data exploration is the process of visualisation of collected data in a graphical format for better understanding to build the project. The data is a complex entity, full of numbers. Hence, to get some sense out of it , data visualization is a must.
Data Visualization
Data visualization is the graphical representation of data. It involves the use of visual elements such as charts, graphs, maps, and infographics to communicate insights, patterns, and trends hidden within the data.
Data visualization helps in
- Understanding complex data more easily.
- Identifying trends, patterns, and correlations.
- Communicating insights clearly and concisely.
- Spotting anomalies and outliers quickly.
- Exploring data interactively.
- Supporting evidence-based decision-making.
Different Ways to Visualize Data
There are some ways to visualize the data as follows Bar Chart It is used to compare categorical data, where the length or height of bars represents the value of each category. It can be vertical or horizontal.
Line Chart It shows trends over time or relationships between variables by connecting data points. It is ideal for displaying continuous data.
Pie Chart It displays parts of a whole, where each segment represents a proportion of the total. It is useful for illustrating percentages or proportions.
Scatter chart It represents individual data points as dots on a two-dimensional graph, with one variable on each axis. It is used to show relationships and correlations between variables.
Histogram It represents the distribution of numerical data by dividing it into intervals, or bins, and displaying the frequency or count of data points falling within each interval. It shows the distribution of values within predefined intervals (bins).
Area Chart It is similar to a line chart but with the area beneath the lines filled in. It is useful for visualizing cumulative totals over time.
Bubble Chart It is similar to a scatter plot but with additional dimensions represented by the size and/or color of bubbles. It allows for the visualization of three or more variables simultaneously.
Modelling Class 10 Notes
In the AI project cycle, modeling is the crucial stage where you translate your problem into a mathematical representation. This involves choosing an algorithm and training it on your data, essentially teaching the AI to recognize patterns and make predictions based on that data. It’s like creating a blueprint for the AI’s decision-making process.
An AI model is a program or algorithm that utilizes a set of data that enables it to recognize certain patterns. This allows it to reach a conclusion or make a prediction when provided with sufficient information.
AI models can be classified into
Rule Based Approach
It refers to the AI modelling where the rules are defined by the developer. The machine follows the rules mentioned by the developer and performs its task accordingly.
These rules are typically expressed in the form of “if-then” statements, where specific actions or decisions are taken based on the satisfaction of certain conditions. Rule-based systems are often used in expert systems, decision support systems, and business process automation.
Rule-based approaches offer several advantages, including:
- Interpretability Rule-based systems are often highly interpretable, as the decision-making process is based on explicit rules that can be easily understood and inspected by humans.
- Transparency Reason behind the system’s decisions is transparent, making it easier to diagnose errors or understand why a particular decision was made.
- Ease of Maintenance Rules can be modified or updated relatively easily, allowing for quick adjustments to accommodate changes in the problem domain.
However, rule-based approaches also have limitations, including:
- Limited Expressiveness Rule-based systems may struggle to capture complex patterns or relationships in the data that cannot be easily expressed as rules.
- Scalability Managing large sets of rules may lead to performance issues, especially as the complexity of the problem domain increases.
Learning Based Approach
In learning based approach, the machine learns by itself. The AI model gets trained on the data fed to it and then it is able to design a model which is adaptive to the change in data. The learning based approach is further divided into three parts. They are:
Supervised Learning
In supervised learning, the model is trained on a labelled dataset, where each input data is paired with corresponding output labels. A label is some information which can be used as a tag for data.
Types of supervised learning model are as follows
Classification It categorizes input data into predefined labels. Classification works on discrete dataset which means the data need not be continuous.
For example, classifying emails as spam or not.
Regression It is used to predict continuous numerical values based on input features. It aims to establish a functional relationship between independent variables and a dependent variable.
For example, predicting house prices based on features like size, bedrooms, and location.
Unsupervised Learning
Unsupervised learning deals with unlabelled data. It does not receive any information regarding the output. The system by itself evaluates and finds out how different elements are related to it.
Types of unsupervised learning model are as follows
Clustering Clustering is the process of grouping unlabelled data into clusters based on their similarities. The goal of clustering is to identify patterns and relationships in the data without any prior knowledge of data. This technique is applied to group data based on different patterns, such as similarities or differences.
For example, finding out which customers made similar product purchases.
Dimensionality Reduction It reduces the number of features, or dimensions, in a dataset. Dimensionality reduction extracts important features from the dataset, reducing the number of irrelevant or random features present.
Reinforcement Learning
Reinforcement learning involves an agent learning to make decisions by interacting with an environment. The agent receives feedback in the form of rewards or punishments based on its actions.
Evaluation Class 10 Notes
The process of testing the project/machine like performance or capabilities and finding faults etc. is known as evaluation. Once a model has been made and trained, it needs to go through proper testing so that one can calculate the efficiency and performance of the model. Hence, the model is tested with the help of Testing Data and the efficiency of the model is calculated on the basis of the parameters mentioned below:
- Accuracy Accuracy is a measure of the overall correctness of the model.
- Precision Precision is the ratio of correctly predicted positive instances to the total predicted positive instances (true positives divided by true positives plus false positives).
- Recall Recall, also known as sensitivity or true positive rate, is the ratio of correctly predicted positive instances to the total actual positive instances (true positives divided by true positives plus false negatives).
- F1 Score The F1 score is the harmonic mean of precision and recall, providing a balanced measure between the two. It is calculated as
2 × \(\frac{\text { Precision } \times \text { Recall }}{\text { Precision }+ \text { Recall }}\)
Neural Networks Class 10 Notes
Neural networks are a fundamental concept in artificial intelligence and machine learning, aligning with your expertise in the field. These networks are inspired by the human brain’s structure and functioning. They are like computer systems inspired by the way our brains work. We use them for tasks like recognizing images, understanding language, and making predictions. One of the best things about them is that they can learn and find patterns in data on their own, without needing specific instructions.
Neural networks are the brains of AI, helping systems learn from data and make smart decisions. They are essential for developing and using AI solutions.
How Neural Network Functions?
Neural networks, simplified into three primary layers-input, hidden, and output-work through interconnected nodes, mimicking the human brain’s functioning.
- Input Layer This layer receives the initial data. Each node represents a feature of the input data. For instance, in image recognition, each node might represent a pixel’s intensity.
- Hidden Layers These layers process the input data through weighted connections. Each node applies a transformation to the data it receives, passing it on to the next layer.
- This layer performs complex calculations to identify patterns in the data.
- Output Layer This layer produces the final result or prediction based on the processed information from the hidden layers. The nodes here represent the possible outcomes or classifications.
- For instance, in a binary classification problem (e.g., spam detection), there might be two nodes representing “spam” or “not spam”.
During the training process, the network adjusts the weights of connections between nodes to minimize the difference between the predicted output and the actual output. This adjustment is done using optimization algorithms like gradient descent. By iteratively adjusting these weights based on the error, neural networks learn to recognize patterns and make predictions. This process is known as training. Once trained, the network can be used to make predictions on new, unseen data.
Features of Neural Network
Some of the features of a Neural Network are listed below:
- They are able to automatically extract features without feeding the input by programmer.
- Every node of layer in a Neural network is compulsorily a machine learning algorithm.
- It is very useful to implement when solving problems for very huge datasets.
Glossary:
- 4Ws Problem Canvas It helps in identifying the key elements related to the problem. The 4Ws are: Who, What, Where, and Why.
- Data Acquisition It refers to the process of collecting, gathering, and preparing data for analysis in an Al project.
- Data Exploration It refers to the initial step in data analysis in which data analysts use data visualization and statistical techniques to describe dataset characterizations.
- Data Visualization It play a crucial role in transforming raw data into visually comprehensible representations.
- Data Modelling It is a crucial step that involves creating a representation of the underlying patterns and relationships within the dataset.
- Neural Networks They are a fundamental concept in artificial intelligence and machine learning, aligning with the human brain’s structure and functioning.
The post AI Project Cycle Class 10 Notes appeared first on Learn CBSE.