Scribd Logo
Upload

Welcome to Scribd!

  • 13 views

    The Future of AI How It Change Our Life

    Uploaded by

    Rizal Mawardi
    The document discusses the history and applications of artificial intelligence and machine learning. It explains different machine learning techniques including supervised learning, unsupervised learning and reinforcement learning. It also describes deep learning, convolutional neural networks and the machine learning workflow.

    Copyright:

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

    The Future of AI How It Change Our Life

    Uploaded by

    Rizal Mawardi
    13 views46 pages
    The document discusses the history and applications of artificial intelligence and machine learning. It explains different machine learning techniques including supervised learning, unsupervised learning and reinforcement learning. It also describes deep learning, convolutional neural networks and the machine learning workflow.

    Original Title

    The Future of AI How It Change Our Life_

    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 discusses the history and applications of artificial intelligence and machine learning. It explains different machine learning techniques including supervised learning, unsupervised learning and reinforcement learning. It also describes deep learning, convolutional neural networks and the machine learning workflow.

    Copyright:

    © All Rights Reserved
    Download as PDF, TXT or read online from Scribd
    Download as pdf or txt
    13 views46 pages

    The Future of AI How It Change Our Life

    Uploaded by

    Rizal Mawardi
    The document discusses the history and applications of artificial intelligence and machine learning. It explains different machine learning techniques including supervised learning, unsupervised learning and reinforcement learning. It also describes deep learning, convolutional neural networks and the machine learning workflow.

    Copyright:

    © All Rights Reserved
    Download as PDF, TXT or read online from Scribd
    Download as pdf or txt
    You are on page 1of 46

    Developing an

    Intelligent
    System with
    Deep Learning
    October 20, 2023
    Elliana Gautama
    The History

    “I propose to
    consider the
    question, ‘Can
    machine think?’”

    Alan Turing Test (1951)


    Application area of AI
    AI is significance to increase the productivity

    Automotive Manufacturing

    Finance

    NLP
    AI
    Healthcare

    Computer Vision Business and


    Education
    Marketing
    Machine with AI vs without AI
    Machine with AI vs without AI

    Customer
    Behavior Analysis Recommender
    System
    Domain Area AI

    01 03 05

    Expert Computer Natural Robotics Fuzzy


    System Vision Language Logic
    Processing
    Machine Learning, Deep Learning vs AI?

    https://blogs.nvidia.com
    Machine Learning

    Machine learning is a subfield of artificial intelligence (AI) that uses algorithms


    trained on data sets to create self-learning models that are capable of predicting
    outcomes and classifying information without human intervention.

    Machine learning is used today for a wide range of commercial purposes, including
    suggesting products to consumers based on their past purchases, predicting stock
    market fluctuations, and translating text from one language to another.

    https://www.coursera.org
    Deep Learning

    Deep learning is a subset of machine learning that is made up of a


    neural network with three or more layers.

    A neural network attempts to model the human brain's behavior by


    learning from large data sets.

    Deep learning drives many AI applications that improve the way


    systems and tools deliver services, such as voice-enabled technology
    and credit card fraud detection.
    https://www.coursera.org
    Types of Learning
    Supervised Learning Unsupervised Learning
    Given: Training Data +
    desired outputs
    01 02 Given: Training Data
    (without desired
    (labels) outputs)

    Semi-Supervised
    Reinforcement Learning
    Learning Given: Training Data +
    Rewards from 04 03 a few desired outputs
    (labels)
    sequence of actions
    Supervised Learning

    https://medium.com/@jorgesleonel/
    Supervised Learning - Classification

    https://www.simplilearn.com/
    Supervised Learning - Regression

    https://www.simplilearn.com/
    Unsupervised Learning

    https://medium.com/@jorgesleonel/
    Unsupervised Learning
    Clustering Association

    Unsupervised
    Learning

    https://www.simplilearn.com/
    Unsupervised Learning – Anomaly
    Detection
    Reinforcement
    Learning

    https://www.simplilearn.com/
    https://www.simplilearn.com/
    Differences between Supervised, Unsupervised, and
    Reinforcement Learning

    https://www.simplilearn.com/
    Machine Learning & Deep Learning Workflow

    https://medium.com/@jorgesleonel/
    Machine Learning Workflow

    https://medium.com/@jorgesleonel/
    https://medium.com/@jorgesleonel/
    Machine Learning vs Deep Learning
    Eight Steps to the Deep Learning
    Process

    Load Preprocess Define Compile


    • Load the data. • Preprocess the data. • Define the model. • Compile the model.

    Fit Evaluate Make Save


    • Fit the model with • Evaluate the model. • Make the predictions • Save the model.
    training data. on new data.
    Convolutional Neural Network (CNN)

    https://medium.com/nafizshahriar/
    Programming a Deep Neural Network from Scratch using MQL Language — Neural Networks — 26 January 2019 — Traders’
    Blogs (mql5.com)
    Performance Measurement
    of ResNet-34 in
    The sixth International Convolutional Neural
    Conference of Computer
    and Informatics Engineering Network Method for
    (The 6th IC2IE) 2023
    Classification of Mask Type
    Usage
    Ari Aziz Rizaldi
    Elliana Gautama
    Collecting
    In this study, the data used came from the Kaggle site
    (https://www.kaggle.com/datasets/omkargurav/face-mask-
    dataset) and also from photos taken by researchers. The amount
    Data of data used is 8.641. The data that has been collected is divided
    into 3 parts, namely medic, non-medic, and without mask.

    non-medic without mask medic


    Preprocessing Data
    Splitting Data
    Data Training
    Data used for model training
    Amount of Data: 5.184

    Data Validation
    60% 30% model validation process and
    preventing overfitting
    Amount of Data: 2.592

    Data Testing
    used for model testing
    Amount of Data: 864

    10%
    Define The Model
    Architecture Model
    Compile the Model
    Fit the Model

    In model training,
    epoch = 15 and
    batch_size = 64.
    Graph of loss Fit Model

    Graph of accuracy Fit Model


    Evaluate the Model

    Accuracy results
    Make the
    Predictions
    In the figure on the side, The test
    results with the new image data show
    that of the nine images tested, there is
    one image that the model predicts
    incorrectly. In the figure, the model
    estimates that the masks used are
    non-medical and should be medical
    masks.
    Comparison of Several Architectures
    Deployment
    Terimakasih

    You might also like

    pFad - Phonifier reborn

    Pfad - The Proxy pFad of © 2024 Garber Painting. All rights reserved.

    Note: This service is not intended for secure transactions such as banking, social media, email, or purchasing. Use at your own risk. We assume no liability whatsoever for broken pages.


    Alternative Proxies:

    Alternative Proxy

    pFad Proxy

    pFad v3 Proxy

    pFad v4 Proxy