Location via proxy:   [ UP ]  
[Report a bug]   [Manage cookies]                
Scribd Logo
Upload

Welcome to Scribd!

  • 11 views

    Machine Learning

    Uploaded by

    darfioussama

    Copyright:

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

    Machine Learning

    Uploaded by

    darfioussama
    11 views21 pages

    Copyright

    © © All Rights Reserved

    Available Formats

    PPTX, PDF, TXT or read online from Scribd

    Did you find this document useful?

    Is this content inappropriate?

    Copyright:

    © All Rights Reserved
    Download as PPTX, PDF, TXT or read online from Scribd
    Download as pptx, pdf, or txt
    11 views21 pages

    Machine Learning

    Uploaded by

    darfioussama

    Copyright:

    © All Rights Reserved
    Download as PPTX, PDF, TXT or read online from Scribd
    Download as pptx, pdf, or txt
    of 21

    Machine

    Learning

    Realised by :
     Aitouaka Mohammed
     Darfi Oussama
    Table of contents
    01 What is ML

    02 Applications

    03 Types

    04 Limitations

    05 Evaluation

    06 Conclusion
    01
    What is Machine Learning?
    • Machine learning is the science of programming machines to think and act like
    humans without being specifically programmed to.

    • We already use machine learning in our daily life without knowing


    it :
    02
    Applications

    (AI)
    Some examples of tasks that are best solved with an ML
    algorithm
    ● Recognizing patterns:
    – Facial identities or facial expressions
    – Handwritten or spoken words
    – Medical images
    ● Generating patterns:
    – Generating images or motion sequences
    ● Recognizing anomalies:
    – Unusual credit card transactions (Fraud
    Detection)
    – Unusual patterns of sensor readings in
    a nuclear power plant
    ● Prediction:
    – Future stock prices or currency exchange
    rates (Forecasting)
    Fields of application
    03
    Types of Machine Learning

    (AI)
    04
    Limitations

    (AI)
    Limitations of Machine Learning

    • Dependence on Labeled Training Data:


    – Acquiring such data can be challenging, time-
    consuming, and costly in some domains.
    – Machine learning algorithms rely heavily on high-
    quality labeled data for training.
    • Adaptability and Continuous Training:
    – Machine learning models may struggle with adapting to
    new or evolving data distributions.
    – Regular updates and retraining are necessary to
    maintain accuracy and relevance in dynamic
    environments.
    • Computational Resource Requirements:
    – Limited computational capabilities may restrict the
    use of certain models or real-time applications.
    05
    Evaluation

    (AI)
    Performance Metrics
     Training and Test Sets
     Performance Metrics for
    Predicted condition
    Classification models:
    • Confusion Matrix Total
    • Accuracy, Precision, Recall, F1 population Positive(PP) Negative(NP)

    Actual condition
    Score. = P+N
    • AUC (Area under the ROC
    curve) False
    True
    Positive(P) negative
     Performance Metrics for Regression positive (TP)
    (FP)
    models:
    • Mean Squared Error (MSE) True
    False
    • Mean Absolute Error (MAE) Negative(N)
    positive(FP)
    negative
    • R2. (TN)
    Underfitting vs Overfitting
    Cross Validation
    06
    Summary

    (AI)
    Thanks!

    Any questions?

    You might also like