Gr10 AI Support Sheet 2024 PDF

Introduction to AI :Fundamentals of AI 1. Define intelligence. a. Ability to interact with the real world b. To perceive, understand and c. Ability to take action: to have an effect d. Solving new problems, planning and making decisions...

Introduction to AI :Fundamentals of AI 1. Define intelligence. a. Ability to interact with the real world b. To perceive, understand and c. Ability to take action: to have an effect d. Solving new problems, planning and making decisions e. Ability to deal with unexpected problems 2 How do you make decisions? The basis of decision making depends upon the availability of information and how we experience and understand it. here, ‘information’ includes our past experience, intuition, knowledge, and self- awareness. 3.How do machines become Artificially Intelligent? Machines become artificially intelligent when they are trained with information to achieve their tasks. AI machines also keep updating their knowledge to optimise the output. 4 What is AI Domain? The training received by an AI machine decides the domain. Basically there are three types of domain- Data Science, Computer vision and Natural Language Processing. 5. What is the main difference between AI and not AI machines? When the machine is able to think and process on its own, it becomes an AI application. An AI machine gets trained first on the training data and then optimises itself according to its own experiences which makes AI different from any other technological device/machine. 6. Explain in brief any three types of intelligence that are mainly perceived by human beings? There are mainly 9 types of Intelligence; (i) Mathematical Logical Intelligence: A person's ability to regulate, measure, and understand numerical symbols, abstraction and logic (ii) Linguistic Intelligence: Language processing skills both in terms of understanding or implementation in writing or speech. (iii) Spatial Visual Intelligence: It is defined as the ability to perceive the visual world and the relationship of one object to another. (iv) Kinesthetic Intelligence: Ability that is related to how a person uses his limbs in a skilled manner. (v) Musical Intelligence: As the name suggests, this intelligence is about a person's ability to recognize and create sounds, rhythms, and sound patterns (vi) Intrapersonal Intelligence: Describes the level of self-awareness someone has starting from realizing weakness, strength, to recognizing his own feelings (vii) Existential Intelligence: An additional category of intelligence relating to religious and spiritual awareness. (viii) Naturalist Intelligence: An additional category of intelligence relating to the ability to process information on the environment around us. (ix) Interpersonal Intelligence: Interpersonal intelligence is the ability to communicate with others by understanding other people's feelings and the influence of the person.  Introduction To AI: Basics Of AI 1. Explain the relation ship between AI ML and DL using a diagram. 2. What is a Neural network? A Neural Network is a series of algorithms that achieve the output after creating relationships on the dataset and processes it like the human brain. What are the applications of Artificial Neural Networks ANN helps in trading based on algorithms, security, classification and forecasting. 3. List the Features of Neural Networks Modelled like neurons in the human brain Organized system of machine learning algorithms to perform certain tasks Able to extract data features automatically fast and efficient way to solve problems with very large dataset such as in images 4.Explain the structure of Artificial Neural network. Input layer It is the first layer of a neural network ;The input layer is responsible to take data and no processing takes place here. Hidden layer It is the layer between the input and output layers. This layer is responsible for processing the input fed into the system. Processing is not visible to anyone and thus is called the hidden layer. Output layer It is the last layer of the neural network. It displays the result as given by the system and no processing takes place here.  AI Project cycle 1. List the stages of AI project cycle. 2. Explain the need of AI project cycle. 3. Define the stages of AI project cycle 1 Problem Scoping- define the goal or aim of your project. 2 Data acquisition- Collect accurate and reliable data 3. Data Exploration- Arrange /organise the collected data uniformly. 4. Modelling- Create models(intelligent algorithms) from the data. 5. Evaluation-Test the reliability of results For that we measures like accuracy, precision, recall, and F1-score. 4. Differentiate between Rule Based and Learning Based algorithms. A Rule based approach is generally based on the data and rules fed to the machine, where the machine reacts accordingly to deliver the desired output.In Learning approach, the machine is fed with data and the desired output to which the machine designs its own algorithm (or set of rules) to match the data to the desired output fed into the machine. 5. Differentiate between Supervised and unsupervised learning. Supervised learning : Algorithm learns from a data set which is labelled. Classification (and Regression come under this categor  Regression Unsupervised learning : the algorithm learns from unlabeled /random data set provided. Clustering comes under this category.  Data Science Applications: 1. Fraud and Risk Detection 2.Genetics & Genomics 3. Internet Search 4.Targeted Advertising 5. Website recommendations 6.Airline Route Planning Sources of Data There exist various sources of data from where we can collect any type of data required and the data collection process can be categorised in two ways: Offline and Online. Points should be kept in mind for data collection: 1. Data available for public usage only should be taken up. 2. Personal datasets should only be used with the consent of the owner. 3. One should never breach someone’s privacy to collect data. 4. Data should only be taken form reliable sources Types of Data- CSV, Spreadsheet, SQL Computer Vision Applications 1.Facial Recognition 2. Face Filters 3. Google’s Search by Image 4. Google Translate App 5.Self driving cars 6. Medical Imaging Computer Vision Tasks Single objects Multiple objects Classification :assigning an input image Object Detection : finding instances of one label from a fixed set of categories. real-world objects Classification + Localisation: identifying Instance Segmentation : detecting the object and its location instances of the objects, Basics of Images: Pixels are the smallest unit of information that make up a picture. Resolution is the number of pixels in an image. Pixel value: describes how bright that pixel is, and/or what colour it should be. Grayscale Images:single channel; Colour/RGB Images:three channel; 0 is considered as black or no presence of colour and 255 means white or full presence of colour.  NLP 1.Explain how AI can play a role in sentiment analysis of human beings? The goal of sentiment analysis is to identify sentiment among several posts or even in the same post where emotion is not always explicitly expressed. Companies use Natural Language Processing applications, such as sentiment analysis, to identify opinions and sentiments online to help them understand what customers think about their products and services. 2 Differentiate between script bot and smart bot. Script-Bot Smart-Bot Limited functions Flexible and powerful Little language skills Wide functionality and can learn with more data Works around a script Coding required 3.Why are human languages complicated for a computer to understand? Explain. a. The communications made by the machines are very basic and simple. Human communication is complex. b. There are multiple characteristics of the human language that might be easy for a human to understand but extremely difficult for a computer to understand. c. Perfect Syntax, no Meaning – a statement can have a perfectly correct syntax but it does not mean anything. In Human language, a perfect balance of syntax and semantics is important for better understanding. 4. What are the steps of text Normalization? Explain them in brief. In, Text Normalization we undergo several steps to normalize the text to a numbers. 1. Sentence Segmentation – Under sentence segmentation, the whole corpus is divided into sentences. So the whole corpus gets reduced to sentences. 2. Tokenisation– o After segmenting the sentences, each sentence is then further divided into tokens. A token is a term used for any word or number or special character occurring in a sentence. 3. Removing Stop words, Special Characters, and Numbers – o In this step, the tokens which are not necessary are removed from the token list. 4. Converting text to a common case – After the stop words removal, we convert the whole text into a similar case, preferably lower case 5. Stemming - In this step, the remaining words are reduced to their root words. stemming is the process in which the affixes of words are removed and the words are converted to their base form. 6. Lemmatization o In lemmatization, the word we get after affix removal (also known as lemma) is a meaningful one. 7. With this, we have normalized our text to tokens which are the simplest form of words present in the corpus. 8. Now it is time to convert the tokens into numbers. For this, we would use the Bag of Words algorithm. 5. List the steps in BoW algorithm. Step 1: Collecting data and pre-processing Step 2: Create Dictionary Step 3: Create document vector for Document 1 Step 4: Repeat for all documents and generate Vector Dictionary Table  Evaluation 1.Define: Evaluation Ans. Evaluation is the process of understanding the reliability of any AI model, based on outputs by feeding the test dataset into the model and comparing it with actual answers. 2. Name two parameters considered for the evaluation of a model. Ans. The two parameters are: 1. Prediction 2. Reality 3.Define overfitting. Ans. The model simply remember the whole training data set and will always predict the correct label for any point in the training set. This is known as overfitting. 1. Rozin is a student of class 10 AI. She wants to know the methods of evaluation. Support her with your answer. Ans.: The evaluation methods are: 1) Accuracy 2) Precision 3) Recall 4) F1 Score 2. Rohit is working on the AI model. He wanted to know the balance between precision and recall. What it is? Ans.: The balance between precision and recall is known F1 score. 3. What are the possible reasons for an AI model not being efficient? Explain. Ans.:Reasons of an AI model not being efficient: a. Lack of Training Data: b. Unauthenticated Data / Wrong Data: c. Inefficient coding / Wrong Algorithms: d. Not Tested: e. Less Accuracy 5. Learn the formula