Scribd Logo
Upload

Welcome to Scribd!

  • 22 views

    Machine Learning

    Uploaded by

    Aly Boy
    The document provides an introduction to machine learning, distinguishing it from artificial intelligence and deep learning, and discussing the different types of learning including supervised, unsupervised, semi-supervised and reinforcement learning. It describes how machine learning works by learning from large amounts of data through training models to make predictions, and provides examples of applications such as recommender systems, computer vision, speech recognition and medical diagnosis.

    Copyright:

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

    Machine Learning

    Uploaded by

    Aly Boy
    22 views27 pages
    The document provides an introduction to machine learning, distinguishing it from artificial intelligence and deep learning, and discussing the different types of learning including supervised, unsupervised, semi-supervised and reinforcement learning. It describes how machine learning works by learning from large amounts of data through training models to make predictions, and provides examples of applications such as recommender systems, computer vision, speech recognition and medical diagnosis.

    Original Description:

    Theory of Data Science

    Original Title

    MachineLearning

    Copyright

    © © All Rights Reserved

    Available Formats

    PDF, TXT or read online from Scribd

    Did you find this document useful?

    Is this content inappropriate?

    The document provides an introduction to machine learning, distinguishing it from artificial intelligence and deep learning, and discussing the different types of learning including supervised, unsupervised, semi-supervised and reinforcement learning. It describes how machine learning works by learning from large amounts of data through training models to make predictions, and provides examples of applications such as recommender systems, computer vision, speech recognition and medical diagnosis.

    Copyright:

    © All Rights Reserved
    Download as PDF, TXT or read online from Scribd
    Download as pdf or txt
    22 views27 pages

    Machine Learning

    Uploaded by

    Aly Boy
    The document provides an introduction to machine learning, distinguishing it from artificial intelligence and deep learning, and discussing the different types of learning including supervised, unsupervised, semi-supervised and reinforcement learning. It describes how machine learning works by learning from large amounts of data through training models to make predictions, and provides examples of applications such as recommender systems, computer vision, speech recognition and medical diagnosis.

    Copyright:

    © All Rights Reserved
    Download as PDF, TXT or read online from Scribd
    Download as pdf or txt
    of 27

    Machine Learning

    DS221 – Spring 2023


    Instructor: Abinta Mehmood
    Outline

    • Introduction to Machine Learning


    • AI vs ML vs DL
    • Learning in ML
    • Applications of ML
    • Types of Learning
    • Examples
    Learning in ML
    Example
    Traditional Programming
    Data
    Computer Output
    Program

    Machine Learning

    Data
    Computer Program
    Output
    AI vs ML vs DL
    AI vs ML vs DL
    • AI is a broader term that describes the capability of the
    machine to learn and solve problems just like humans.

    • A small algorithmic rule for self-driving car can be:


    if distance_from_in_front <100m:
    stop();
    else:
    keep_moving();

    • There are two ways of incorporating intelligence in artificial


    things i.e., to achieve artificial intelligence. One is through
    machine learning and another is through deep learning.
    AI vs ML vs DL
    • Machine Learning:
    “Technique to learn from data through training and then apply
    learning to make an informed decision”
    • Analyzing and learning from data comes under the training
    part of the machine learning model.

    • “Difference between the predicted and actual value is computed using loss-
    function or objective function. Therefore, defining the objective/loss function
    is the gist of ML model.”
    • Examples: weather forecasting, Netflix recommendations, stock prediction,
    to malware detection.
    • For example, in the case of recommending items to a user, the objective is
    to minimize the difference between the predicted rating of an item by the
    model and the actual rating given by the user.
    .
    AI vs ML vs DL
    Deep Learning – The Future
    • It is based on an artificial neural network which is nothing but a mimic of
    the working of the human brain.
    • Just like the ML model, the DL model requires a large amount of data to
    learn and make an informed decision and is therefore also considered a
    subset of ML.
    • DL models do not require any feature extraction pre-processing step and
    are capable of classifying data into different classes and categories
    themselves.
    • Without DL, Alexa, Siri, Google Voice Assistant, Google Translation, Self-
    driving cars are not possible
    • Raw Data is given to DL model. Pre-processed data is given to ML model.
    • Deep Learning is seen as a rocket whose fuel is data.
    Types of Learning

    • Supervised (inductive) learning


    – Training data includes desired outputs
    • Unsupervised learning
    – Training data does not include desired outputs
    • Semi-supervised learning
    – Training data includes a few desired outputs
    • Reinforcement learning
    – Rewards from sequence of actions
    Types of Learning
    • Supervised learning
    – Regression
    – Classification
    • Unsupervised learning
    – Clustering
    – Dimensionality reduction

    Data can be numerical and categorial


    Numerical: age, id, weight, gpa etc.
    Categorial: Gender, Nationality, Cat/Dog etc.
    Steps Involved
    Training Training
    Labels
    Training
    Images
    Image Learned
    Training
    Features model

    Testing

    Image Learned
    Prediction
    Features model
    Test Image Slide credit: D. Hoiem and L. Lazebnik
    Features

    • Raw pixels

    • Histograms

    • GIST descriptors

    Slide credit: L. Lazebnik


    Learning Associations

    • Basket analysis:
    P (Y | X ) probability that somebody who
    buys X also buys Y where X and Y are
    products/services.

    Example: P ( chips | coke ) = 0.7

    19
    Classification
    • Example:
    Credit scoring
    • Differentiating
    between low-
    risk and high-
    risk customers
    from their
    income and
    savings Discriminant: IF income > θ1 AND savings > θ2
    THEN low-risk ELSE high-risk
    20
    Classification: Applications
    • Aka Pattern recognition
    • Face recognition: Pose, lighting, occlusion
    (glasses, beard), make-up, hair style
    • Character recognition: Different handwriting
    styles.
    • Speech recognition: Temporal dependency.
    – Use of a dictionary or the syntax of the language.
    – Sensor fusion: Combine multiple modalities; eg,
    visual (lip image) and acoustic for speech
    • Medical diagnosis: From symptoms to
    illnesses 21
    Face Recognition

    Training examples of a person

    Test images

    AT&T Laboratories, Cambridge UK


    http://www.uk.research.att.com/facedatabase.html
    22
    Regression

    • Example: Price of
    a used car
    y = wx+w0
    • x : car attributes
    y : price
    y = g (x | θ )
    g ( ) model,
    θ parameters
    23
    Unsupervised Learning
    • Learning “what normally happens”
    • No output
    • Clustering: Grouping similar instances
    • Example applications
    – Customer segmentation
    – Image compression: Color quantization
    – Bioinformatics

    24
    Unsupervised Learning

    25
    Reinforcement Learning

    • Learning a policy: A sequence of outputs


    • No supervised output but delayed reward
    • Game playing
    • Robot in a maze
    • Multiple agents, partial observability, ...

    26

    You might also like