Scribd Logo
Upload

Welcome to Scribd!

  • Day 3-FDP

    Uploaded by

    shamilie17
    10 views30 pages
    The document provides an overview of deep learning and neural networks. It defines deep learning as a type of machine learning based on artificial neural networks that can perform supervised, semi-supervised, or unsupervised learning. Neural networks are modeled after the human brain and can learn from data to recognize patterns and make decisions. Convolutional neural networks are effective for computer vision tasks like image classification and involve stacking convolutional and pooling layers to analyze images.

    Original Description:

    Copyright

    © © All Rights Reserved

    Available Formats

    PDF, TXT or read online from Scribd

    Did you find this document useful?

    Is this content inappropriate?

    Report this Document
    The document provides an overview of deep learning and neural networks. It defines deep learning as a type of machine learning based on artificial neural networks that can perform supervised, semi-supervised, or unsupervised learning. Neural networks are modeled after the human brain and can learn from data to recognize patterns and make decisions. Convolutional neural networks are effective for computer vision tasks like image classification and involve stacking convolutional and pooling layers to analyze images.

    Copyright:

    © All Rights Reserved
    Download as PDF, TXT or read online from Scribd
    Flag for inappropriate content
    Download as pdf or txt
    10 views30 pages

    Day 3-FDP

    Uploaded by

    shamilie17
    The document provides an overview of deep learning and neural networks. It defines deep learning as a type of machine learning based on artificial neural networks that can perform supervised, semi-supervised, or unsupervised learning. Neural networks are modeled after the human brain and can learn from data to recognize patterns and make decisions. Convolutional neural networks are effective for computer vision tasks like image classification and involve stacking convolutional and pooling layers to analyze images.

    Copyright:

    © All Rights Reserved
    Download as PDF, TXT or read online from Scribd
    Flag for inappropriate content
    Download as pdf or txt
    of 30

    DEEP LEARNING

    Disclaimer: The content is curated for educational purposes only.


    © Edunet Foundation. All rights reserved.
    Agenda
    ● Deep Learning & Neural Networks
    ● ANN Architectural Components
    ● Computer Vision
    ● Convolutional Neural Networks

    © Edunet Foundation. All rights reserved.


    Deep Learning
    ● Also known as "deep structured learning"

    ● Part of a broader family of machine learning


    methods

    ● Based on artificial neural networks

    ● Learning can be supervised, semi-supervised


    or unsupervised

    https://careers.edicomgroup.com/wp-content/uploads/2021/03/DeepLearning-2.jpg

    © Edunet Foundation. All rights reserved.


    What is a neural network?

    • Artificial replica of densely interconnected brain cells inside


    • it can learn things, recognize patterns, and make decisions in a
    humanlike way.
    • One don't have to program it to learn explicitly: it learns all by
    itself, just like a brain!

    © Edunet Foundation. All rights reserved.


    Application of Neural Networks
    • Machine Diagnostics
    • Target Recognition
    • Medical Diagnosis
    • Face & Voice recognition
    • Fraud detection

    © Edunet Foundation. All rights reserved.


    Components

    © Edunet Foundation. All rights reserved.


    2 Layer Architecture

    © Edunet Foundation. All rights reserved.


    Single Neuron

    https://www.analyticsvidhya.com/blog/2020/02/cnn-vs-rnn-vs-mlp-analyzing-3-types-of-neural-
    networks-in-deep-learning/
    © Edunet Foundation. All rights reserved.
    Activation Function

    © Edunet Foundation. All rights reserved.


    Working of ANN

    © Edunet Foundation. All rights reserved.


    Training a Neural Network

    © Edunet Foundation. All rights reserved.


    Loss Functions
    A loss function, that can be used to estimate the loss of the
    model so that the weights can be updated to reduce the loss
    on the next evaluation.

    © Edunet Foundation. All rights reserved.


    Gradient Descent

    © Edunet Foundation. All rights reserved.


    https://blog.paperspace.com/intro-to-optimization-in-deep-learning-gradient-descent/

    © Edunet Foundation. All rights reserved.


    https://blog.paperspace.com/intro-to-optimization-in-deep-learning-gradient-descent/

    © Edunet Foundation. All rights reserved.


    COMPUTER VISION
    Gaining High-level understanding from digital images or videos

    Disclaimer: The content is curated for educational purposes only.


    © Edunet Foundation. All rights reserved.
    Popular Python Libraries

    © Edunet Foundation. All rights reserved.


    What is an Image?
    Data in the form of matrix(Rows and Columns) consisting of Pixels

    © Edunet Foundation. All rights reserved.


    Types of Images

    Color Image Grayscale Image Binary Image

    https://www.researchgate.net/profile/Sanskruti-Patel-2/publication/
    © Edunet Foundation. All rights reserved.
    Color Image Width * Height * Depth

    Depth : [Red, Green, Blue]

    https://www.codeproject.com/KB/tips/1112774/rgbPixelEx.PNG

    © Edunet Foundation. All rights reserved.


    CONVOLUTIONAL
    NEURAL NETWORK
    Effective at Dealing with Image Data

    © Edunet Foundation. All rights reserved.


    CNNs have stacked layered architecture of several
    Convolution and Pooling Layers
    © Edunet Foundation. All rights reserved.
    Kernel

    © Edunet Foundation. All rights reserved.


    Kernel

    © Edunet Foundation. All rights reserved.


    Convolutions

    © Edunet Foundation. All rights reserved.


    Convolutions

    © Edunet Foundation. All rights reserved.


    Stride

    © Edunet Foundation. All rights reserved.


    Pooling

    © Edunet Foundation. All rights reserved.


    Pooling

    © Edunet Foundation. All rights reserved.


    Thank You

    © Edunet Foundation. All rights reserved.

    You might also like