Scribd Logo
Upload

Welcome to Scribd!

  • 12 views

    AI Session 2

    Uploaded by

    Gunjan Suman
    The document discusses key concepts in artificial intelligence including: 1. Data is the lifeblood of AI and important for training algorithms to find patterns. 2. Common algorithms used in AI include statistical algorithms like Bayes classifiers and structural algorithms like k-means clustering. 3. Data quality and bias are important considerations, and increasing data, features, or model complexity can help reduce bias and variance.

    Copyright:

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

    AI Session 2

    Uploaded by

    Gunjan Suman
    12 views64 pages
    The document discusses key concepts in artificial intelligence including: 1. Data is the lifeblood of AI and important for training algorithms to find patterns. 2. Common algorithms used in AI include statistical algorithms like Bayes classifiers and structural algorithms like k-means clustering. 3. Data quality and bias are important considerations, and increasing data, features, or model complexity can help reduce bias and variance.

    Copyright

    © © All Rights Reserved

    Available Formats

    PPTX, PDF, TXT or read online from Scribd

    Did you find this document useful?

    Is this content inappropriate?

    The document discusses key concepts in artificial intelligence including: 1. Data is the lifeblood of AI and important for training algorithms to find patterns. 2. Common algorithms used in AI include statistical algorithms like Bayes classifiers and structural algorithms like k-means clustering. 3. Data quality and bias are important considerations, and increasing data, features, or model complexity can help reduce bias and variance.

    Copyright:

    © All Rights Reserved
    Download as PPTX, PDF, TXT or read online from Scribd
    Download as pptx, pdf, or txt
    12 views64 pages

    AI Session 2

    Uploaded by

    Gunjan Suman
    The document discusses key concepts in artificial intelligence including: 1. Data is the lifeblood of AI and important for training algorithms to find patterns. 2. Common algorithms used in AI include statistical algorithms like Bayes classifiers and structural algorithms like k-means clustering. 3. Data quality and bias are important considerations, and increasing data, features, or model complexity can help reduce bias and variance.

    Copyright:

    © All Rights Reserved
    Download as PPTX, PDF, TXT or read online from Scribd
    Download as pptx, pdf, or txt
    of 64

    Artificial Intelligence

    School of Computer Engineering and Technology

    Dr. Sharmishta Desai


    Module-II
    1. Data as Lifeblood of AI

    2. Algorithms for finding patterns to work with data using AI

    3. Data Quality and Bias

    2
    3
    AI and Machine Learning

    Are they Same????????

    4
    Which is the world’s most complex system????

    5
    Human Brain

    6
    7
    What if machines behave like Human Brain…

    8
    9
    How do Humans Learn?

    10
    School of CET,MITWPU,Pune
    School of CET,MITWPU,Pune
    To learn from past experiences…………………

    School of CET,MITWPU,Pune
    That is nothing but………………………………

    Machine Learning

    School of CET,MITWPU,Pune
    School of CET,MITWPU,Pune
    School of CET,MITWPU,Pune
    School of CET,MITWPU,Pune
    Data as Lifeblood of AI
    Why does AI, machine learning Works

    School of CET,MITWPU,Pune
    Data as Lifeblood of AI
    Principle of AI, Machine
    Learning

    MORE DATA> BETTER MODEL>HIGHER ACCURACY

    School of CET,MITWPU,Pune
    Data as Lifeblood of AI
    • The collection of data is a critical element of AI and machine
    learning
    • A data labeling has an extremely important role to play in
    ensuring the correct data is collected.
    • It is the input that will be utilized to drive the algorithms that
    drive artificial intelligence.
    • Data is essential to the learning and decision-making processes
    of the AI system.
    • It is therefore important to collect high-quality data that is
    relevant to the AI project.
    • Data can be structured or unstructured data, text, images,
    audio, or video, depending on the need of application
    School of CET,MITWPU,Pune
    Algorithms for Finding Patterns
    • Statistical Algorithms-Bayes Classifier
    • Structural Algorithms- K-means Clustering
    • Neural Network-ANN

    School of CET,MITWPU,Pune
    Statistical Algorithms

    School of CET,MITWPU,Pune
    School of CET,MITWPU,Pune
    School of CET,MITWPU,Pune
    Structural Algorithms

    School of CET,MITWPU,Pune
    Structural Algorithms

    School of CET,MITWPU,Pune
    Structural Algorithms

    School of CET,MITWPU,Pune
    Can you guess labels: Bowlers /
    Batsmen

    School of CET,MITWPU,Pune
    School of CET,MITWPU,Pune
    School of CET,MITWPU,Pune
    Unsupervised Learning

    School of CET,MITWPU,Pune
    School of CET,MITWPU,Pune
    School of CET,MITWPU,Pune
    School of CET,MITWPU,Pune
    School of CET,MITWPU,Pune
    School of CET,MITWPU,Pune
    School of CET,MITWPU,Pune
    School of CET,MITWPU,Pune
    School of CET,MITWPU,Pune
    K Means Clustering Algorithm

    School of CET,MITWPU,Pune
    School of CET,MITWPU,Pune
    School of CET,MITWPU,Pune
    Data Quality and Bias

    School of CET,MITWPU,Pune
    Data Quality and Bias

    School of CET,MITWPU,Pune
    Data Quality and Bias

    School of CET,MITWPU,Pune
    Data Quality and Bias

    School of CET,MITWPU,Pune
    Data Quality and Bias

    School of CET,MITWPU,Pune
    Data Quality and Bias

    School of CET,MITWPU,Pune
    Data Quality and Bias

    School of CET,MITWPU,Pune
    Ways to reduce high bias in Machine
    Learning
    • Use a more complex model: One of the main reasons for high
    bias is the very simplified model. it will not be able to capture the
    complexity of the data. In such cases, we can make our mode
    more complex by increasing the number of hidden layers in the
    case of a deep neural network.

    • Increase the number of features: By adding more features to


    train the dataset will increase the complexity of the model. And
    improve its ability to capture the underlying patterns in the data.

    • Increase the size of the training data: Increasing the size of the
    training data can help to reduce bias by providing the model with
    more examples to learn from the dataset.
    School of CET,MITWPU,Pune
    Data Quality and Bias

    School of CET,MITWPU,Pune
    Data Quality and Bias

    School of CET,MITWPU,Pune
    Data Quality and Bias

    School of CET,MITWPU,Pune
    Ways to Reduce Variance in
    Machine Learning
    • Cross-validation: By splitting the data into training and testing
    sets multiple times, cross-validation can help identify if a model is
    overfitting or underfitting and can be used to tune
    hyperparameters to reduce variance.

    • Feature selection: By choosing the only relevant feature will


    decrease the model’s complexity. and it can reduce the variance
    error.

    • Early stopping: Early stopping is a technique used to prevent


    overfitting by stopping the training of the deep learning model
    when the performance on the validation set stops improving.

    School of CET,MITWPU,Pune
    Difference in actual and predicted value is called
    as----------------------------

    School of CET,MITWPU,Pune
    Good AI Model will have --------------bias and ---------
    Variance

    School of CET,MITWPU,Pune
    In K-means Clustering what is significance of K……

    School of CET,MITWPU,Pune
    Evaluation Measures
    • Accuracy
    • Precision
    • Recall

    School of CET,MITWPU,Pune
    Precision Vs Recall
    Perfect precision score of 1.0 means that every result
    retrieved by a search was relevant (but says nothing
    about whether all relevant documents were
    retrieved)

    Perfect recall score of 1.0 means that all relevant


    documents were retrieved by the search (but says
    nothing about how many irrelevant documents were
    also retrieved).

    School of CET,MITWPU,Pune
    Quiz?

    School of CET,MITWPU,Pune
    Precision Vs Recall
    • Search Engine
    • Youtube
    • Email Spam
    • Cancer detection

    School of CET,MITWPU,Pune
    School of CET,MITWPU,Pune
    School of CET,MITWPU,Pune
    Thank you

    School of CET,MITWPU,Pune

    You might also like