Unit 4

Learning & Applications of AI

Learning–Forms of Learning,
Supervised Learning,
Machine Learning-Decision Trees,
Regression and Classification with Linear Models,
Artificial Neural Networks,
Support Vector Machines.

Applications of AI-Natural Language Processing,

Text Classification and Information Retrieval,
Speech Recognition,
Image processing and computer vision,
Robotics.
Natural Language Processing (NLP)

• Natural Language Processing (NLP) is a branch of artificial intelligence

that focuses on enabling computers to understand, interpret, and
generate human language.

• It allows machines to process and analyze both written and spoken

language, making it possible for them to interact with humans in a
more natural and intuitive way.
Concepts

Understanding Human Language:

NLP aims to bridge the gap between human language (natural language) and computer
systems, allowing machines to comprehend the meaning, intent, and context of text and speech.

AI and Linguistics:
NLP combines principles from computer science, artificial intelligence, and linguistics (the study
of language).

Machine Learning:
Modern NLP models are often built using machine learning techniques, allowing them to learn
from large amounts of data and improve their language processing abilities over time.
Key Areas of NLP

•Natural Language Understanding (NLU): This involves enabling computers to grasp

the meaning and context of human language.

•Natural Language Generation (NLG): This focuses on enabling computers to produce

human-quality text or speech.

•Speech Recognition: Converting spoken language into text.

•Text Classification: Categorizing text into different classes or categories.

•Machine Translation: Translating text from one language to another.

Applications of NLP:

NLP has a wide range of applications, including:

•Chatbots and Virtual Assistants: Powering conversational interfaces like Siri, Alexa, and chatbots for customer
service.

•Search Engines: Improving the accuracy and relevance of search results by understanding user queries.

•Sentiment Analysis: Determining the emotional tone or sentiment expressed in text (e.g., positive, negative,
neutral).

•Spam Detection: Identifying and filtering out unwanted emails or messages.

•Information Extraction: Automatically extracting relevant information from text data.

•Text Summarization: Generating concise summaries of lengthy texts.

NLP is a rapidly evolving field that is transforming how humans interact with technology, making it more
accessible and intuitive.
 Image processing and computer vision
• Image processing is a method used to perform operations on an image to enhance it or extract useful
information. It is a type of signal processing where the input is an image, such as a photograph or video frame,
and the output may be either an image or a set of characteristics or parameters related to the image. Image
processing involves the manipulation of digital images through a digital computer.
• It has a wide range of applications in various fields such as medical imaging, remote sensing, surveillance,
industrial inspection, and more.

Some basic techniques used in image processing:

• Filtering: This technique is used to enhance or change the appearance of an image. For example, filters can make
images look sharper or blurrier.
• Segmentation: This technique involves breaking up a picture into manageable chunks for easy analysis. For
example distinguishing the foreground from the backdrop.
• Edge Detection: The process of identifying boundaries or edges inside a picture such as an object or person
outline is known as edge detection.
• Morphological Processing: The process of morphological processing involves analyzing an image's object shape
or structure in order to reduce noise and fill in any gaps.
 Basic Steps in AI Image Processing Implementation
Step Description

Data Collection Gathering images for training

Preprocessing Preparing images (resizing, filtering, etc.)

Training Teaching the AI model with data

Evaluation Testing the model with new images

Deployment Using the model in real-world applications

Role of AI in Image Processing

AI has the ability to learn from millions of images and then apply that understanding to fresh image processing and
understanding. AI is applied in image processing in the following ways:
• Object Recognition: AI is able to recognize things in images, such as the difference between a dog and a cat.
• Facial Recognition: This involves recognizing and verifying human faces, used in security systems and social media.
• Image Enhancement: AI can enhance images by making them clearer in cases where they are unclear.
• Image Generation: AI is capable of producing original visuals such as lifelike portraits of made-up persons or artwork.
 What is computer vision?
• Computer vision is a field of artificial intelligence (AI) that uses machine learning and neural
networks to teach computers and systems to derive meaningful information from digital images,
videos and other visual inputs—and to make recommendations or take actions when they see
defects or issues.

• If AI enables computers to think, computer vision enables them to see, observe and understand.

• Computer vision works much the same as human vision, except humans have a head start. Human
sight has the advantage of lifetimes of context to train how to tell objects apart, how far away they
are, whether they are moving or something is wrong with an image.

• Computer vision trains machines to perform these functions, but it must do it in much less time by
using cameras, data and algorithms in place of retinas, optic nerves and a visual cortex. Because a
system trained to inspect products or watch a production asset can analyze thousands of products or
processes a minute, noticing imperceptible defects or issues, it can quickly surpass human
capabilities.

• Computer vision is used in industries that range from energy and utilities to manufacturing and
automotive—and the market is continuing to grow.
Here are a few examples of established computer vision tasks:
• Image classification sees an image and can classify it (a dog, an apple, a person’s face). More precisely, it
is able to accurately predict that a given image belongs to a certain class. For example, a social media
company might want to use it to automatically identify and segregate objectionable images uploaded by
users.

• Object detection can use image classification to identify a certain class of image and then detect and
tabulate their appearance in an image or video. Examples include detecting damages on an assembly
line or identifying machinery that requires maintenance.

• Object tracking follows or tracks an object once it is detected. This task is often executed with images
captured in sequence or real-time video feeds. Autonomous vehicles, for example, need to not only
classify and detect objects such as pedestrians, other cars and road infrastructure, they need to track
them in motion to avoid collisions and obey traffic laws.[7]

• Content-based image retrieval uses computer vision to browse, search and retrieve images from large
data stores, based on the content of the images rather than metadata tags associated with them. This
task can incorporate automatic image annotation that replaces manual image tagging. These tasks can
be used for digital asset management systems and can increase the accuracy of search and retrieval.
 Robotics
• Robotics is a field of science that is responsible for designing and creating machines
to reduce human effort. Robots are capable of not just substituting human effort, but
also sensing the environment and adapting themselves according to it.

• Robots are a combination of hardware as well as software working in sync with each
other.

• Artificial intelligence and robotics are a strong combination for automating tasks
inside and out of doors of the factory setting.

• In recent years, AI has become an increasingly common presence in robotic solutions,

introducing flexibility and learning capabilities in previously rigid applications
• Applications of AI in Robotics
• AI in robotics is transforming industries by enabling robots to autonomously
perform tasks that were once reliant on human intervention. Below are some key
applications of AI in robotics, with real-life examples of how this technology is being
utilized.

• Autonomous Navigation: AI-powered robots can autonomously navigate through

complex environments, making decisions in real-time using data from sensors. This
is especially useful in industries like logistics and manufacturing.

• Machine Learning for Predictive Maintenance: Machine learning algorithms in AI-

powered robots can analyze sensor data to predict equipment failures before they
occur. This reduces downtime and ensures that industrial processes run smoothly.

• Surgical Robotics with AI Assistance: AI is revolutionizing healthcare, particularly in

surgical robotics. AI-powered robots assist surgeons in performing complex
procedures with greater precision, using real-time data analysis to enhance
decision-making.
• AI-Powered Inspection and Quality Control: In manufacturing, AI-powered robots
equipped with computer vision technology can inspect products for defects and
ensure high-quality standards.

• AI for Search and Rescue Operations: AI-powered robots are crucial in disaster
response efforts, capable of navigating through dangerous or hard-to-reach areas to
find survivors and assess damage.

• Human-Robot Collaboration: AI has enabled robots to collaborate with human

workers, taking over monotonous tasks and allowing humans to focus on higher-
level problem-solving. This enhances productivity and safety in various industries.

• Personalization and Customer Service: AI-powered robots are also being used to
enhance customer service by providing personalized experiences and interacting
with customers in real-time.
 AO* algorithm in Artificial intelligence (AI)

• The AO* algorithm is an advanced search algorithm utilized in artificial intelligence,

particularly in problem-solving and decision-making contexts. It is an extension of the
A* algorithm, designed to handle more complex problems that require handling
multiple paths and making decisions at each node.

• The AO algorithm* (short for "And-Or Star") is a powerful best-first search method
used to solve problems that can be represented as a directed acyclic graph (DAG).
Unlike traditional algorithms like A*, which explore a single path, the AO* algorithm
evaluates multiple paths simultaneously.

• This makes it more efficient for problems that involve AND-OR nodes. The AND nodes
represent tasks where all child nodes must be satisfied, while OR nodes offer multiple
alternative paths where only one child node needs to be satisfied to achieve the goal.
Comparison between A* Algorithm and AO* algorithm

Aspect A* Algorithm AO* Algorithm

Search Type Best-first search Best-first search

Type of Search Informed search using heuristics Informed search using heuristics

Solution Optimality Always gives the optimal solution Does not guarantee an optimal solution

Path Exploration Explores all possible paths Stops exploring once a solution is found

Memory Usage Uses more memory Uses less memory

May go into an endless loop without

Endless Loop Cannot go into an endless loop
proper checks