Scribd Logo
Upload

Welcome to Scribd!

  • 3.2 Machine Learning Concepts

    Uploaded by

    OmarFernandez
    10 views7 pages
    Here are some potential disadvantages of machine learning: - Bias in data - If the data used to train machine learning models is biased or non-representative, it can result in systems that discriminate unfairly. - Lack of explainability - Complex machine learning models can be difficult for humans to understand or explain their decisions. This is known as the "black box" problem. - Brittleness - Machine learning systems tend to break if data shifts in unexpected ways after deployment. They may need frequent retraining to adapt to new situations. - Privacy and security issues - Data used to train systems may contain private information that could be leaked or misused if not properly secured. Systems can also potentially be manipulated or

    Original Description:

    Original Title

    3.2 Machine Learning Concepts (6)

    Copyright

    © © All Rights Reserved

    Available Formats

    PPTX, PDF, TXT or read online from Scribd

    Did you find this document useful?

    Is this content inappropriate?

    Report this Document
    Here are some potential disadvantages of machine learning: - Bias in data - If the data used to train machine learning models is biased or non-representative, it can result in systems that discriminate unfairly. - Lack of explainability - Complex machine learning models can be difficult for humans to understand or explain their decisions. This is known as the "black box" problem. - Brittleness - Machine learning systems tend to break if data shifts in unexpected ways after deployment. They may need frequent retraining to adapt to new situations. - Privacy and security issues - Data used to train systems may contain private information that could be leaked or misused if not properly secured. Systems can also potentially be manipulated or

    Copyright:

    © All Rights Reserved
    Download as PPTX, PDF, TXT or read online from Scribd
    Flag for inappropriate content
    10 views7 pages

    3.2 Machine Learning Concepts

    Uploaded by

    OmarFernandez
    Here are some potential disadvantages of machine learning: - Bias in data - If the data used to train machine learning models is biased or non-representative, it can result in systems that discriminate unfairly. - Lack of explainability - Complex machine learning models can be difficult for humans to understand or explain their decisions. This is known as the "black box" problem. - Brittleness - Machine learning systems tend to break if data shifts in unexpected ways after deployment. They may need frequent retraining to adapt to new situations. - Privacy and security issues - Data used to train systems may contain private information that could be leaked or misused if not properly secured. Systems can also potentially be manipulated or

    Copyright:

    © All Rights Reserved
    Download as PPTX, PDF, TXT or read online from Scribd
    Flag for inappropriate content
    of 7

    Machine Learning

    Concepts
    Machine Learning

    1. the ability to automatically learn.


    2. improve from experience without being explicitly programmed.
    3. can access data and use it to learn for themselves.
    4. the computers learn automatically without human intervention or
    assistance
    5. adjust actions accordingly.

    “a method by which a computer program can “automatically learn


    and improve from experience without being explicitly
    programmed.”
    Machine learning algorithms are often categorized as:

    1. Supervised Machine Learning

    1. applies what has been learned in the past to new data using labeled
    examples to predict future events.

    2. able to provide targets for any new input after sufficient training.

    3. learning algorithm can also compare its output with the correct, intended
    output

    4. find errors in order to modify the model accordingly.


    Machine learning algorithms are often categorized as:

    2. Unsupervised Machine Learning

    1. the information used to train is neither classified nor labeled.

    2. systems can infer a function to describe a hidden structure from unlabeled


    data.

    3. doesn’t figure out the right output, but it explores the data.

    4. can draw inferences from datasets to describe hidden structures from


    unlabeled data.
    Machine learning algorithms are often categorized as:

    3. Semi-supervised Machine Learning

    1. falls between supervised and unsupervised learning.

    2. they use both labeled and unlabeled data for training – typically a small
    amount of labeled data and a large amount of unlabeled data.

    3. able to considerably improve learning accuracy.

    4. is chosen when the acquired labeled data requires skilled and relevant
    resources in order to train it / learn from it.
    Machine learning algorithms are often categorized as:

    4. Reinforcement Machine Learning

    1. interacts with its environment by producing actions and discovers


    errors or rewards.

    2. use Trial and error search and delayed reward

    3. automatically determine the ideal behavior within a specific context in


    order to maximize its performance.
    Question 1 of 4

    What possible dis-advantage can machine learning do?

    You might also like