Udemy
    •  
    •  
    •  
    •  
    •  
    •  
    •  
    •  
Subscribe
Turn what you know into an opportunity and reach millions around the world.
Learn More
Your cart is empty.
Keep shopping
ANNs and DNNs 0 to 100 | Python | Machine Learning | AI
Rating: 4.9 out of 5(5 ratings)
38 students

ANNs and DNNs 0 to 100 | Python | Machine Learning | AI

Linear Classifier | SVM | Regularization | Softmax | Gradient Descent | Backpropagation | DNN | Dropout | CNN
Created byGhazal Lalooha
Last updated 2/2025
English

What you'll learn

  • Linear Classification
  • Cost function of multi-class SVM
  • Overfitting and Regularization
  • Softmax cost function
  • Cost function optimization
  • Gradient Descent Algorithm
  • Back Propagation Algorithm
  • Multi-layer artificial neural networks
  • Deep Neural Networks
  • Problem Solving with Artificial Neural Networks
  • Advanced Optimization methods
  • Drop out usage in DNN training
  • CNN

Explore related topics

Coding Exercises

This course includes our updated coding exercises so you can practice your skills as you learn.

See a demo
Image of coding exercise example

Course content

3 sections • 17 lectures • 4h 42m total length

  • Linear Classifiers18:28
  • Multi-class SVM cost function10:32
  • Overfitting and Regularization4:24
  • Softmax cost function4:15
  • Cost function optimization2:58
  • Gradient Descent Algorithm9:58
  • Back propagation algorithm11:40

    Explore computational graphs and the backpropagation algorithm: compute loss and gradients via forward and backward passes, with data loss, regularization, nodes, topological order, and gradient rules.

  • Multi-layer artificial neural networks20:03
  • Deep Neural Networks17:17
  • Problem solving through artificial neural networks12:39
  • Advanced optimization methods10:49
  • Dropout in artificial neural training9:04

    Dropout combats overfitting by randomly zeroing a fraction of hidden-layer outputs during training, using masks and scaling; it is not applied in the output layer or test phase.

  • Convolutional Neural Networks15:47

    Learn how convolutional neural networks extract features from images through layered convolution, ReLU, padding, stride, and pooling, producing feature maps for classification.

  • Exercise 1
  • Exercise 2
  • Linear Classification
  • Multiclass SVM cost function
  • Regularization
  • Softmax
  • Optimization
  • Gradient Descent
  • Back propagation algorithm
  • Multi-layer artificial neural networks.
  • Deep Neural Networks
  • Problem-solving through ANNs.
  • Advanced optimization methods.
  • Dropout in artificial neural training
  • Convolutional Neural Networks

Requirements

  • familiarity with Python programming language
  • basic familiarity with Machine Learning

Description

Embark on a comprehensive journey to master Artificial Neural Networks (ANNs) and Deep Neural Networks (DNNs) with my expertly structured course. Designed for both beginners and those looking to deepen their understanding, this course offers a blend of theoretical concepts and practical coding exercises in Python.

Key Topics Covered:

Linear Classifiers: Understand the foundation of classification algorithms and their role in machine learning.

Support Vector Machines (SVM): Dive into SVMs, the powerful supervised learning models used for classification and regression.

Overfitting and Regularization: Learn how to identify overfitting in your models and techniques to regularize and prevent it.

Softmax: Master the Softmax function for multi-class classification problems.

Gradient Descent: Grasp the optimization method crucial for training neural networks.

Backpropagation: Gain insight into the algorithm that adjusts weights in the network to minimize error.

Deep Neural Networks (DNNs): Explore advanced architectures and how they can vastly improve model performance.

Dropout: Implement dropout techniques to prevent overfitting in deep learning models.

Convolutional Neural Networks (CNNs): Delve into CNNs for image processing and other applications.

Course Features:

Comprehensive **Python coding files** and references are provided to enhance hands-on learning.

Detailed explanatory sessions combined with practical assignments.

Step-by-step guidance through each topic, ensuring a solid understanding of basic concepts to advanced techniques.

By the end of this course, you will possess a robust understanding of both theoretical and practical aspects of neural networks, equipped to tackle complex machine learning challenges with confidence.

Join now and transform your understanding of ANNs and DNNs from 0 to 100!

Who this course is for:

  • everyone who wants to get promotion in his job(in every field of work)

Report abuse