Scribd Logo
Upload

Welcome to Scribd!

  • 4 views

    Copy of Indian AI Tech Project Proposal by Slidesgo

    Uploaded by

    MOHIT SAVLIYA

    Copyright:

    © All Rights Reserved
    Download as PDF, TXT or read online from Scribd

    Copy of Indian AI Tech Project Proposal by Slidesgo

    Uploaded by

    MOHIT SAVLIYA
    4 views16 pages

    Copyright

    © © All Rights Reserved

    Available Formats

    PDF, TXT or read online from Scribd

    Did you find this document useful?

    Is this content inappropriate?

    Copyright:

    © All Rights Reserved
    Download as PDF, TXT or read online from Scribd
    Download as pdf or txt
    4 views16 pages

    Copy of Indian AI Tech Project Proposal by Slidesgo

    Uploaded by

    MOHIT SAVLIYA

    Copyright:

    © All Rights Reserved
    Download as PDF, TXT or read online from Scribd
    Download as pdf or txt
    You are on page 1of 16

    AI REASONING AND

    PROCESSES
    BY MOHIT, JATIN, KARTIK, BRIAN
    01
    REASONING IN AI
    An overview of how artificial
    intelligence works
    REASONING
    REASONING can be defined as the logical
    process of drawing conclusions, making
    predictions, or constructing solutions
    based on existing knowledge. In Artificial

    AI Intelligence, reasoning plays a crucial role


    in understanding how the human brain
    thinks, draws conclusions, and solves
    problems. Through reasoning, AI systems
    can simulate human-like decision-making
    and problem-solving capabilities. Let’s dive
    into the different types of reasoning used in
    AI.
    01 DEDUCTIVE REASONING

    DIFFERENT TYPES OF
    INDUCTIVE REASONING
    02 REASONING

    ABDUCTIVE REASONING
    03
    DEDUCTIVE
    REASONING
    Definition: Deductive reasoning starts with
    a general statement or hypothesis and
    examines the possibilities to reach a
    specific, logical conclusion. It's a top-down
    approach.

    ● General Rule (Premise): All birds can


    fly.
    ● Specific Case: A robin is a bird.
    ● Conclusion: Therefore, a robin can fly.

    USED IN EXPERT SYSTEM WHERE RULES ARE


    CLEARLY MENTIONED
    INDUCTIVE REASONING
    Definition: Inductive reasoning allows AI to learn
    patterns and make predictions by analyzing data
    and identifying trends. Unlike deductive
    reasoning, which guarantees the conclusion if the
    premises are true, inductive reasoning deals with
    probabilities and generalizations.

    ● Specific Observations: All swans observed


    in a specific region are white.
    ● Generalization: Therefore, all swans are
    white (until a counterexample, like a black
    swan, is found).

    THEY ARE USED IN MACHINE LEARNING, LEARNING


    PATTERNS
    ABDUCTIVE REASONING
    Abductive Reasoning:

    ● Definition: Forms the best possible hypothesis to explain


    incomplete or ambiguous information.
    ● Example: If an AI system observes wet streets, it may
    hypothesize that "it rained recently," though other
    explanations (like a water fight) are possible.

    Abductive reasoning is used in diagnostic systems,


    such as medical diagnosis tools or fault detection
    systems, where the goal is to identify the most
    probable cause of a problem given incomplete data.
    ANALOGICAL REASONING
    Analogical reasoning compares two situations that
    share similarities, using knowledge from one domain to
    solve problems in another. This reasoning allows AI
    systems to draw parallels between similar scenarios.
    ● If flying a drone is similar to piloting a
    helicopter, knowledge gained from helicopter
    control can be applied to drones

    Analogical reasoning is useful in AI for


    problem-solving, decision-making, and knowledge
    transfer, especially in robotics and cognitive
    02
    KNOWLEDGE REPRESENTATION
    IN AI
    An overview of how artificial
    intelligence works
    KNOWLEDGE
    REPRESENTATION IN AI

    Knowledge representation in AI
    is all about how we structure
    and store information so that
    machines can understand and
    use it effectively. Here are some
    key methods
    WHAT WE ARE WORKING ON

    SEMANTIC NETWORKS FRAMES ONTOLOGIES


    Ontologies are like a structured map of
    These are graph Frames are data structures knowledge. Imagine you have a big box
    of Lego pieces, each piece representing a
    structures that represent for representing different concept or idea. An ontology
    knowledge in terms of stereotypical situations. helps you organize these pieces by
    showing how they fit together and relate
    entities and their They are like templates that to each other. It defines categories,
    hold information about properties, and relationships between
    relationships concepts in a specific domain, making it
    objects and their attributes easier for both humans and machines to
    understand and use the information.
    03
    PROCESSES IN AI
    An overview of how artificial
    intelligence works
    Processes in AI refer to the various steps and
    methods used to develop, train, and deploy
    artificial intelligence systems. These
    processes ensure that AI systems can learn
    from data, make decisions, and perform tasks
    effectively. ”
    MAJOR REQUIREMENTS
    DATA COLLECTION
    Gathering relevant data FEATURE
    from various sources
    to serve as the
    EXTRACTION
    foundation for training Identifying and
    AI models.
    DATA
    selecting important
    PREPROCESSING features from the data
    Cleaning and organizing the that will be used to
    collected data to make it train the AI model,
    suitable for analysis, including reducing complexity
    handling missing values and and improving
    removing noise. performance.
    The processes in AI offer numerous advantages that contribute to the efficiency, accuracy, and overall
    capabilities of AI systems. Here are some of the key benefits:

    1. Enhanced Data Utilization: AI processes, such as data collection and preprocessing,


    allow for the efficient use of vast amounts of data, turning raw information into valuable insights.
    2. Improved Model Accuracy: Feature extraction and model selection ensure that AI
    systems are built on relevant and high-quality data, leading to more accurate and reliable
    outcomes.
    3. Speed and Efficiency: Training and evaluation processes enable AI models to learn and
    adapt quickly, providing fast and efficient solutions to complex problems.
    4. Consistency and Precision: Automated processes minimize human error and ensure
    consistent performance, particularly in repetitive tasks.
    5. Scalability: AI processes can be scaled to handle large datasets and workloads, making them
    suitable for applications ranging from small-scale projects to enterprise-level solutions.
    THANKS!

    CREDITS: This presentation template was created by


    Slidesgo, including icons by Flaticon and infographics &
    images by Freepik

    You might also like