Class 10 AI

Artificial Intelligence Grade - X CBSE – 2025-26 www.cbseinfotech.blogspot.com Visit Our Website CBSE INFOTECH

Revisiting AI Project Cycle & Ethical Frameworks for AI Unit - 1 CBSE INFOTECH

Learning Outcomes ▪ Outline the six stages of the AI Project Cycle. ▪ Elucidate the AI domains and their applications. ▪ Describe what are frameworks and ethical frameworks. ▪ Classify ethical frameworks based on sectors and value addition. ▪ Explore the bioethical framework and its principles in detail. ▪ Practice the application of an ethical framework for AI. CBSE INFOTECH

AI Project Cycle 1.1 CBSE INFOTECH

AI Project Cycle Problem Scoping Data Acquisition Data Exploration Modelling Evaluation Deployment CBSE INFOTECH

AI Project Cycle • Problem Scoping: We look at various parameters which affect the problem we wish to solve so that the picture becomes clearer. • Data acquisition: By collecting data from various reliable and authentic sources. • Exploration: Visual image of different types of representations like graphs, databases, flow charts, maps, etc. • Modelling: After exploring the patterns, you can research online and select various models which give a suitable output. • Test the selected models and figure out which is the most efficient one. • Test your model on some newly fetched data. The results will help you in evaluating your model and improving it. • Finally, after evaluation, the deployment stage is crucial for ensuring the successful integration and operation of AI solutions in real-world environments, enabling them to deliver value and impact to users and stakeholders. CBSE INFOTECH

Introduction to AI Domains 1.2 CBSE INFOTECH

AI models can be broadly categorized into three domains: Statistical Data Computer Vision Natural Language Processing CBSE INFOTECH

Statistical Data • The quantitative information collected and analyzed to understand patterns, trends, and relationships within a dataset. • This data is typically numerical and can be used to train machine learning models, make predictions, and inform decision-making. • Common characteristics of statistical data in AI include: 1. Quantitative: Statistical data is numerical in nature, allowing for mathematical operations and analysis. 2. Structured: Statistical data is often organized into tables, datasets, or other structured formats, making it easier to analyze and process. 3. Large-scale: Statistical data in AI often involves large datasets, which can be analyzed using machine learning algorithms and statistical techniques. 4. Variable: Statistical data can include various types of variables, such as categorical, numerical, or ordinal variables. CBSE INFOTECH

Examples of statistical data in AI include: • Sensor readings: Temperature, pressure, or motion sensor data from IoT devices. • Customer transactions: Purchase history, demographics, and behavioural data from customers. • Medical records: Patient health data, medical histories, and treatment outcomes. • Image and video data: Pixel values, object detection, and image classification data. • Price Comparison Websites: These websites are being driven by lots and lots of data. If you have ever used these websites, you would know, the convenience of comparing the price of a product from multiple vendors in one place. CBSE INFOTECH

Computer Vision • Depicts the capability of a machine to get and analyse visual information and afterwards predict some decisions about it. • The entire process involves image acquiring, screening, analysing, identifying and extracting information. • Computer Vision (CV) in AI refers to the field of study that enables computers to interpret, understand, and make decisions from visual data, such as images and videos. • Input to machines can be photographs, videos and pictures from thermal or infrared sensors, indicators and different sources. • It involves training machines to extract meaningful information from visual inputs, mimicking the human visual system. CBSE INFOTECH

CV in AI encompasses various tasks.. • Image Classification: Identifying objects, scenes, or activities within images. • Object Detection: Locating and classifying objects within images or videos. • Image Segmentation: Dividing images into regions or segments based on pixel characteristics. • Image Generation: Creating new images or modifying existing ones using generative models. • Image-to-Image Translation: Transferring styles or content from one image to another. • Video Analysis: Analyzing and understanding video content, including object tracking and action recognition. CBSE INFOTECH

CV has numerous applications in AI: • Self-Driving Cars: CV is used for lane detection, object recognition, and navigation. • Facial Recognition: CV is used for identity verification, security, and surveillance. • Medical Imaging: CV is used for disease diagnosis, tumor detection, and image analysis. • Robotics: CV is used for object recognition, grasping, and manipulation. • Surveillance: CV is used for monitoring and analyzing video feeds. • Agricultural Monitoring: pest detection, and yield estimation, Drones with cameras capture aerial images of farmland, which are then analysed to assess crop health and optimize farming practices. CBSE INFOTECH

Natural Language Processing • The field of study that enables computers to understand, interpret, and generate human language. • NLP combines computer science, artificial intelligence, and linguistics to analyze, process, and generate natural language data. CBSE INFOTECH

NLP in AI involves various tasks, including: • Text Classification: Categorizing text into predefined categories, such as spam vs. non-spam emails. • Sentiment Analysis: Determining the emotional tone or sentiment of text, such as positive, negative, or neutral. • Named Entity Recognition (NER): Identifying named entities, such as people, organizations, and locations, within text. • Part-of-Speech (POS) Tagging: Identifying the grammatical category of each word, such as noun, verb, or adjective. • Machine Translation: Translating text from one language to another. • Question Answering: Answering questions based on the content of text. • Text Summarization: Summarizing long pieces of text into shorter summaries. CBSE INFOTECH

NLP has numerous applications in AI: • Virtual Assistants: Siri, Alexa, and Google Assistant use NLP to understand voice commands. • Language Translation Apps: Google Translate and Microsoft Translator use NLP for machine translation. • Sentiment Analysis Tools: Tools like Hootsuite and Sprout Social use NLP for sentiment analysis. • Chatbots: Many chatbots use NLP to understand and respond to user queries. CBSE INFOTECH

NLP has numerous applications in AI: • Email Filters: Email filters are one of the most basic and initial applications of NLP online. It started with spam filters, uncovering certain words or phrases that signal a spam message. • Machine Translation: NLP is used in machine translation systems like Google Translate and Microsoft Translator to automatically translate text from one language to another. These systems analyze the structure and semantics of sentences in the source language and generate equivalent translations in the target language. CBSE INFOTECH

NLP relies on various techniques, including: • Tokenization: Breaking down text into individual words or tokens. • Stemming and Lemmatization: Reducing words to their base form. • Named Entity Recognition (NER): Identifying named entities within text. • Deep Learning: Using neural networks to analyze and process natural language data. CBSE INFOTECH

Ethical Frameworks for AI 1.3 CBSE INFOTECH

Framework • Set of steps that help us in solving problems.. • structured approach to problem-solving, ensuring that all relevant factors and considerations are taken into account. • The sharing of best practices and promoting consistency in problem- solving methodologies. CBSE INFOTECH

Ethical Frameworks • Ethics are a set of values or morals which help us separate right from wrong. • Help us ensure that the choices we make do not cause unintended harm. • A systematic approach to navigating complex moral dilemmas by considering various ethical principles and perspectives. • Can make well- informed decisions that align with their values and promote positive outcomes for all stakeholders involved. CBSE INFOTECH

• AI is essentially being used as a decision-making/ influencing tool. As such we need to ensure that AI makes morally acceptable recommendations. • Think of the hiring algorithm which was biased against women applicants! • Ethical frameworks ensure that AI makes morally acceptable choices.. • We can avoid unintended outcomes, even before they take place! Why do we need Ethical Frameworks for AI? CBSE INFOTECH

Activity: 1 My Goodness https://www.my-goodness.net/ CBSE INFOTECH

Activity: 1 My Goodness CBSE INFOTECH

Types of Ethical Frameworks These classifications provide a structured approach for addressing ethical concerns in AI development and deployment, ensuring that considerations relevant to specific sectors and fundamental ethical values are adequately addressed. CBSE INFOTECH

Sector-based Frameworks: • In the context of AI, one common sector-based framework is Bioethics, which focuses on ethical considerations in healthcare. • It addresses issues such as patient privacy, data security, and the ethical use of AI in medical decision- making. Sector-based ethical frameworks may also apply to domains such as finance, education, transportation, agriculture, governance, and law enforcement. CBSE INFOTECH

Value-based Frameworks: • Focus on fundamental ethical principles and values guiding decision- making. • It reflects the different moral philosophies that inform ethical reasoning. • Value-based frameworks are concerned with assessing the moral worth of actions and guiding ethical behaviour. CBSE INFOTECH

Value-based Frameworks: Rights-based: • Prioritizes the protection of human rights and dignity, valuing human life over other considerations. • It emphasizes the importance of respecting individual autonomy, dignity, and freedoms. • In the context of AI, this could involve ensuring that AI systems do not violate human rights or discriminate against certain groups. CBSE INFOTECH

Value-based Frameworks: Utility-based: • Evaluates actions based on the principle of maximizing utility or overall good, aiming to achieve outcomes that offer the greatest benefit and minimize harm. • maximize overall utility or benefit for the greatest number of people. • Weighing the potential benefits of AI applications against the risks they pose to society, such as job displacement or privacy concerns. CBSE INFOTECH

Value-based Frameworks: Virtue-based: • Focuses on the character and intentions of the individuals involved in decision- making. • It asks whether the actions of individuals or organizations align with virtuous principles such as honesty, compassion, and integrity. • In the context of AI, virtue ethics could involve considering whether developers, users, and regulators uphold ethical values throughout the AI lifecycle. CBSE INFOTECH

Bioethics (A Sector-based Frameworks) • An ethical framework used in healthcare and life sciences. • It deals with ethical issues related to health, medicine, and biological sciences, ensuring that AI applications in healthcare adhere to ethical standards and considerations. CBSE INFOTECH

Principles of bioethics: • Respect for Autonomy. • Do not harm. • Ensure maximum benefit for all. • Give justice. CBSE INFOTECH

Non-maleficence “Non-maleficence” refers to the ethical principle of avoiding causing harm or negative consequences. It emphasizes the obligation to minimize harm as much as possible and prioritize actions that prevent harm to individuals, communities, or the environment. Non-maleficence is a fundamental principle in bioethics that means "do no harm." CBSE INFOTECH

Non-maleficence “Maleficence” refers to the concept of intentionally causing harm or wrongdoing. Non-maleficence is a fundamental principle in bioethics that means "do no harm." CBSE INFOTECH

Beneficence “Beneficence" refers to the ethical principle of promoting and maximizing the well-being and welfare of individuals and society. It emphasizes taking actions that produce positive outcomes and contribute to the overall good, ensuring that the greatest benefit is achieved for all stakeholders involved. CBSE INFOTECH

Case Study - 1 CBSE INFOTECH

CBSE INFOTECH

Advanced Concepts of Modeling in AI Unit - 2 CBSE INFOTECH

Learning Outcomes ▪ Understand AI, ML and DL. ▪ Familiarize with supervised, unsupervised and reinforcement learning based approach. ▪ Understand subcategories of Supervised, Unsupervised and deep learning models. ▪ Understand Neural Networks. ▪ Understand how AI makes a decision. CBSE INFOTECH

2.1 Revisiting AI ML DL CBSE INFOTECH

Differentiate between AI, ML, and DL Artificial Intelligence, or AI for short, refers to any technique that enables computers to mimic human intelligence. An artificially intelligent machine works on algorithms and data fed to it and gives the desired output. CBSE INFOTECH

Differentiate between AI, ML, and DL Machine Learning, or ML for short, enables machines to improve at tasks with experience. The machine here learns from the new data fed to it while testing and uses it for the next iteration. It also takes into account the times when it went wrong and considers the exceptions too. CBSE INFOTECH

Differentiate between AI, ML, and DL Deep Learning, or DL for short, enables software to train itself to perform tasks with vast amounts of data. Since the system has got huge set of data, it is able to train itself with the help of multiple machine learning algorithms working altogether to perform a specific task. CBSE INFOTECH

Differentiate between AI, ML, and DL “Artificial Intelligence is the umbrella term which holds both Deep Learning as well as Machine Learning. Deep Learning, on the other hand, is the very specific learning approach which is a subset of Machine Learning as it comprises of multiple Machine Learning algorithms.” CBSE INFOTECH

Differentiate between AI, ML, and DL Image Source: https://blog.nilayparikh.com/the-perennial-debate-of-artificial-intelligence-ai-versus-machine- learning-ml-93b526925318 The ability of a machine to imitate human intelligence. ML is a subset of AI. Algorithms that enables machines To learn from data and make decisions. DL is a subset of ML. Algorithms inspired by the structure of a human brain (based on ann) CBSE INFOTECH

Machine Learning Machine Learning, or ML, enables machines to improve at tasks with experience. The machine learns from its mistakes and takes them into consideration in the next execution. It improvises itself using its own experiences. CBSE INFOTECH

Examples of Machine Learning Object Classification Identifies and labels objects present within an image or data point. It determines the category an object belongs to. CBSE INFOTECH

Examples of Machine Learning Anomaly Detection Anomaly detection helps us find the unexpected things hiding in our data. For example, tracking your heart rate, and finding a sudden spike could be an anomaly, flagging a potential issue. CBSE INFOTECH

Machine Learning Machine Learning (ML) is a subset of Artificial Intelligence (AI) that enables systems to learn from data, identify patterns, and make predictions or decisions without being explicitly programmed. In simpler terms, Machine Learning is a way to train computers to learn from experience and improve their performance on a task over time, without being told exactly what to do. Some key characteristics of Machine Learning include: 1. Learning from data: ML algorithms use data to learn patterns and relationships. 2. Improving performance: ML models improve their performance on a task over time, based on the data they receive. 3. Autonomy: ML systems can make decisions or predictions without human intervention. CBSE INFOTECH

Machine Learning has many applications, including: 1. Image recognition: self-driving cars, facial recognition 2. Natural Language Processing: chatbots, language translation 3. Recommendation systems: product recommendations, personalized ads 4. Predictive maintenance: predicting equipment failures, maintenance scheduling 5. Predictive Modelling: forecasting, risk analysis, recommendation systems 6. Classification: spam detection, sentiment analysis, image classification 7. Clustering: customer segmentation, anomaly detection 8. Regression: predicting continuous outcomes, like house prices 1. Supervised Learning: learning from labelled data 2. Unsupervised Learning: learning from unlabelled data 3. Reinforcement Learning: learning through trial and error There are several types of Machine Learning, including: CBSE INFOTECH

Deep Learning Deep Learning, or DL, enables software to train itself to perform tasks with vast amounts of data. In deep learning, the machine is trained with huge amounts of data which helps it into training itself around the data. Such machines are intelligent enough to develop algorithms for themselves. Deep Learning is the most advanced form of Artificial Intelligence out of these three. CBSE INFOTECH

Examples of Deep Learning Object Identification Object classification in deep learning tackles the task of identifying and labelling objects within an image. It essentially uses powerful algorithms to figure out what's in a picture and categorize those things CBSE INFOTECH

Examples of Deep Learning Digit Recognition Digit recognition in deep learning tackles the challenge of training computers to identify handwritten digits (0-9) within images. CBSE INFOTECH

Deep Learning Deep Learning (DL) is a subset of Machine Learning (ML) that uses artificial neural networks with multiple layers to learn complex patterns in data. Some key characteristics of Deep Learning include: 1. Neural Networks: DL models are based on artificial neural networks, inspired by the human brain. 2. Multiple Layers: DL models have multiple layers of nodes (neurons) that process and transform inputs. 3. Representation Learning: DL models learn to represent complex data in a hierarchical manner. CBSE INFOTECH

Deep Learning has many applications, including: 1. Computer Vision: image recognition, object detection, segmentation. 2. Natural Language Processing: language modelling, text classification, machine translation. 3. Speech Recognition: speech-to-text systems. 4. Game Playing: AlphaGo, game playing AI. 1. Convolutional Neural Networks (CNNs): for image and signal processing 2. Recurrent Neural Networks (RNNs): for sequential data, like text or speech 3. Generative Adversarial Networks (GANs): for generating new data samples There are several types of Deep Learning, including: CBSE INFOTECH

Deep Learning has many applications, including: Point Machine Learning (ML) Deep Learning (DL) 1. Definition Subset of AI that uses algorithms to learn from data. Subset of ML that uses neural networks with many layers. 2. Data Requirement Works well with smaller datasets. Requires large amounts of data to perform well. 3. Feature Engineering Manual feature extraction is usually needed. Automatically extracts features using neural networks. 4. Model Complexity Uses simpler models (e.g., decision trees, SVM). Uses complex architectures like CNNs, RNNs, Transformers. 5. Hardware Dependency Can run on regular CPUs. Often requires GPUs or TPUs due to high computation. 6. Training Time Typically faster to train. Training can take a lot of time. 7. Interpretability Easier to interpret and understand. Often considered a "black box" – harder to interpret. 8. Examples Spam detection, credit scoring, recommendation systems. Image recognition, speech-to-text, language translation. 9. Accuracy Good accuracy with proper features. Generally achieves higher accuracy with enough data. 10. Flexibility Less flexible for unstructured data. Very effective with unstructured data (images, audio, text). CBSE INFOTECH

Common terminologies used with data CBSE INFOTECH

What is Data? 1. Data is information in any form. 2. For e.g. A table with information about fruits is data. 3. Each row will contain information about different fruits. 4. Each fruit is described by certain features CBSE INFOTECH

What do you mean by Features? 1. Columns of the tables are called features. 2. In the fruit dataset example, features may be name, color, size, etc. 3. Some features are special, they are called labels. CBSE INFOTECH

What are Labels? 1. Data Labelling is the process of attaching meaning to data. 2. It depends on the context of the problem we are trying to solve. 3. For e.g. if we are trying to predict what fruit it is based on the colour of the fruit, then colour is the feature, and fruit name is the label. 4. Data can be of two types – Labelled and Unlabelled CBSE INFOTECH

Labelled Data Data to which some tag/label is attached. For e.g. Name, type, number, etc. Unlabelled Data The raw form of data Data to which no tag is attached. CBSE INFOTECH

What do you mean by a training data set? 1. The training data set is a collection of examples given to the model to analyse and learn. 2. Just like how a teacher teaches a topic to the class through a lot of examples and illustrations. 3. Similarly, a set of labelled data is used to train the AI model. CBSE INFOTECH

What do you mean by a testing data set? 1. The testing data set is used to test the accuracy of the model. 2. Just like how a teacher takes a class test related to a topic to evaluate the understanding level of students. 3. Test is performed without labelled data and then verify results with labels. CBSE INFOTECH

2.2 : Modelling CBSE INFOTECH

AI Models CBSE INFOTECH

Rule Based Approach 1. Defined by the developer. 2. The machine follows the rules or instructions mentioned by the developer, and performs its task accordingly. 3. Rule-based Chatbots are commonly used on websites to answer frequently asked questions (FAQs) or provide basic customer support. For example: A clothing website has a Chabot to answer questions about order tracking. (When a user chats with the bot, their message is analysed based on the defined rules. The Chabot responds with a pre-written answer or prompts the user for additional information depending on the scenario.) CBSE INFOTECH

Rule Based Approach - drawback 1. The learning is static. 2. The machine once trained, does not take into consideration any changes made in the original training dataset. If you try testing the machine on a dataset which is different from the rules and data you fed it at the training stage, the machine will fail and will not learn from its mistake. Once trained, the model cannot improvise itself on the basis of feedbacks. Thus, machine learning gets introduced as an extension to this as in that case, the machine adapts to change in data and rules and follows the updated path only, while a rule-based model does what it has been taught once. CBSE INFOTECH

Learning Based Approach A learning-based approach is a method where a computer learns how to do something by looking at examples or getting feedback, similar to how we learn from experience. Instead of being explicitly programmed for a task, the computer learns to perform it by analysing data and finding patterns or rules on its own. CBSE INFOTECH

Learning Based Approach For example, suppose you have a dataset of 1000 images of random stray dogs of your area. Now you do not have any clue as to what trend is being followed in this dataset as you don’t know their breed, or colour or any other feature. Thus, you would put this into a learning approach-based AI machine and the machine would come up with various patterns it has observed in the features of these 1000 images. It might cluster the data on the basis of colour, size, fur style, etc. It might also come up with some very unusual clustering algorithm which you might not have even thought of! CBSE INFOTECH

Learning Based Approach • AI modelling where the machine learns by itself. • AI model gets trained on the data fed to it and then is able to design a model which is adaptive to the change in data. • if the model is trained with X type of data and the machine designs the algorithm around it, the model would modify itself according to the changes which occur in the data so that all the exceptions are handled in this case. For example, A learning-based spam email filter is a computer program that automatically identifies whether an incoming email is spam or not. Instead of being explicitly programmed with rules for identifying spam, the filter learns from examples of labelled emails during a training phase. CBSE INFOTECH

Rule Based v/s Learning Based Approach Rule-Based Approach 1.Logic is manually defined using if-then rules. 2.No learning from data – system behaviour is static. 3.Created and maintained by domain experts. 4.Transparent and explainable – you can see how decisions are made. 5.Works well for simple, well-defined problems. 6.Scales poorly – more rules = more complexity. 7.Struggles with ambiguity or unstructured data (like images or natural language). Learning-Based Approach (Machine Learning) 1.Learns from data to make predictions or decisions. 2.Improves performance with more data and experience. 3.Created by training models (e.g., neural networks, decision trees). 4.Often a black box – hard to interpret how decisions are made. 5.Ideal for complex, high-dimensional tasks. 6.Scales well with big data. 7.Can handle noisy, unstructured data effectively. CBSE INFOTECH

Rule Based v/s Learning Based Approach CBSE INFOTECH

Categories of Machine learning based models CBSE INFOTECH

Supervised Learning • The dataset which is fed to the machine is labelled. • A label is some information which can be used as a tag for data. For example, students get grades according to the marks they secure in examinations. These grades are labels which categorize the students according to their marks. • Supervised Learning indicates having a supervisor as a teacher For e.g. A math teacher teaches the class by making the students learn using a lot of solved examples(training) and then test the knowledge gained by giving the class, problems to solve on their own. CBSE INFOTECH

Supervised Learning CBSE INFOTECH

Supervised Learning Dogs CBSE INFOTECH

Unsupervised Learning • The dataset which is fed to the machine is unlabelled. • This means that the data which is fed to the machine is random and there is a possibility that the person who is training the model does not have any information regarding it. • Models are used to identify relationships, patterns and trends out of the data which is fed into it. • It helps the user in understanding what the data is about and whatare the major features identified by the machine in it. CBSE INFOTECH

Unsupervised Learning For example, you have a random data of 1000 dog images and you wish to understand some pattern out of it, you would feed this data into the unsupervised learning model and would train the machine on it. After training, the machine would come up with patterns which it was able to identify out of it. The Machine might come up with patterns which are already known to the user like colour or it might even come up with something very unusual like the size of the dogs. CBSE INFOTECH

Unsupervised Learning • Unsupervised Learning is a type of learning without any guidance • For e.g. A child learning to swim on his own without any supervision. Here, the child is the model trying to discover ways and techniques to swim and the swimming pool is similar to the unknown data fed to the model. • Here, the machine is responsible to discover patterns, similarities, and differences on its own based on the unlabelled dataset. CBSE INFOTECH

Unsupervised Learning CBSE INFOTECH

Test Yourself: Identify the model: Supervised or Unsupervised? CBSE INFOTECH

Supervised & Unsupervised Learning CBSE INFOTECH

Reinforcement Learning This learning approach enables the computer to make a series of decisions that maximize a reward metric for the task without human intervention and without being explicitly programmed to achieve the task. CBSE INFOTECH

Reinforcement Learning CBSE INFOTECH

Summary of ML Modelling CBSE INFOTECH

Subcategory of Supervised Learning CBSE INFOTECH

Classification CBSE INFOTECH

Classification Example CBSE INFOTECH

Regression CBSE INFOTECH

Regression Example CBSE INFOTECH

Test yourself? CBSE INFOTECH

Classification V/S Regression CBSE INFOTECH

Subcategories of Unsupervised learning model CBSE INFOTECH

Clustering CBSE INFOTECH The two clusters have been formed based on the similarity of characteristics. The first cluster comprises all the animals, and the second cluster comprises all the birds.

Clustering V/S Classification CBSE INFOTECH

Clustering – Example CBSE INFOTECH

Association CBSE INFOTECH Association Rule is an unsupervised learning method that is used to find interesting relationships between variables from the database.

Association CBSE INFOTECH

Association examples CBSE INFOTECH

Summary of detailed classification of ML models CBSE INFOTECH

Test Yourself CBSE INFOTECH Supervised Learning Classification Regression

Test Yourself CBSE INFOTECH Unsupervised, Divide the data points into different groups Predicts a continuous value as output

Subcategories of Deep Learning CBSE INFOTECH

Subcategories of Deep Learning CBSE INFOTECH ther

Neural Network

ANN

ANN Real-world applications of neural network are facial recognition, customer support chatbot, vegetable price prediction etc.

ANN Applications Handwritten Character Recognition ANNs are used for handwritten character recognition. Neural Networks are trained to recognize the handwritten characters which can be in the form of letters or digits. Data Source: https://data-flair.training/blogs/artificial-neural-networks-for-machine-learning/

ANN Applications Speech Recognition ANNs play an important role in speech recognition. The earlier models of Speech Recognition were based on statistical models like Hidden Markov Models. With the advent of deep learning, various types of neural networks are the absolute choice for obtaining an accurate classification. Data Source: https://data-flair.training/blogs/artificial-neural-networks-for-machine-learning/

ANN Applications Signature Classification For recognizing signatures and categorizing them to the person’s class, we use artificial neural networks for building these systems for authentication. Furthermore, neural networks can also classify if the signature is fake or not. Data Source: https://data-flair.training/blogs/artificial-neural-networks-for-machine-learning/

ANN Applications Facial Recognition In order to recognize the faces based on the identity of the person, we make use of neural networks. They are most commonly used in areas where the users require security access. Convolutional Neural Networks are the most popular type of ANN used in this field. Data Source: https://data-flair.training/blogs/artificial-neural-networks-for-machine-learning/

CNN • Convolutional Neural Networks are a type of Deep Learning Algorithm that take the image as an input and learn the various features of the image through filters. • Learn the important objects present in the image, allowing them to discern one image from the other. For example, the convolutional network will learn the specific features of cats that differentiate from the dogs so that when we provide input of cats and dogs, it can easily differentiate between the two. • Its ability to pre-process the data by itself. Thus, you may not spend a lot of resources in data pre-processing. Data Source: https://data-flair.training/blogs/artificial-neural-networks-for-machine-learning/

CNN Data Source: https://data-flair.training/blogs/artificial-neural-networks-for-machine-learning/

CNN Examples 1. Self-Driving Cars: CNNs are used in self-driving cars to detect objects, lanes, and road signs. 2. Facial Recognition: CNNs are used in facial recognition systems, such as those used in security and surveillance. 3. Image Classification: CNNs can classify images into categories, such as objects, scenes, and actions. 4. Object Detection: CNNs can detect objects in images and videos, such as pedestrians, cars, and animals. 5. Medical Image Analysis: CNNs can analyse medical images, such as tumours, fractures, and diabetic retinopathy. Some examples of CNNs in action include:- Google's AlphaGo AI, which defeated a human world champion in Go- Facebook's facial recognition system, which identifies and tags friends in photos- Tesla's Autopilot system, which uses CNNs to detect and respond to road conditions

How does AI make a Decision?

How does AI make a Decision? Let's say you want to go out to the park today. What would be your thought process? What would you consider?

How does AI make a Decision?

How does AI make a Decision? Now let us convert this to perceptron.

Perceptron: How does AI make a Decision?

How does AI make a Decision?

From this calculation, the output is 0.5. Since this is higher than the threshold (which is zero), the result is I will go out to the park.

From this calculation, the output is -0.5. Since this is lower than the threshold (which is zero), the result is I will not go out to the park.

Thank You For Your Attention CBSE INFOTECH https://cbseinfotech.blogspot.com/ Visit Our WebsiteCBSE INFOTECH https://www.youtube.com/@CBSEINFOTECH