Convolutional Neural Networks with TensorFlow in Python

Master Convolutional Neural Networks: Building advanced neural network models with TensorFlow

4 hours of content 6460 students

$99.00

Lifetime access

Buy now
14-Day Money-Back Guarantee

What you get:

  • 4 hours of content
  • 24 Downloadable resources
  • Interactive exercises
  • World-class instructor
  • Closed captions
  • Q&A support
  • Future course updates
  • Course exam
  • Certificate of achievement

Convolutional Neural Networks with TensorFlow in Python

$99.00

Lifetime access

Buy now
14-Day Money-Back Guarantee

What you get:

  • 4 hours of content
  • 24 Downloadable resources
  • Interactive exercises
  • World-class instructor
  • Closed captions
  • Q&A support
  • Future course updates
  • Course exam
  • Certificate of achievement

$99.00

Lifetime access

Buy now
14-Day Money-Back Guarantee

What you get:

  • 4 hours of content
  • 24 Downloadable resources
  • Interactive exercises
  • World-class instructor
  • Closed captions
  • Q&A support
  • Future course updates
  • Course exam
  • Certificate of achievement

What You Learn

  • Master convolutional neural networks (CNNs) and computer vision to develop cutting-edge visual recognition systems
  • Improve your career prospects by acquiring advanced deep learning skills with TensorFlow
  • Adopt proven optimization techniques used to optimize the performance of neural networks
  • Master TensorBoard, TensorFlow’s indispensable visualization tool
  • Apply TensorFlow to solve complex real-world computer vision challenges
  • Strategically position your profile to capitalize on the ever-growing number of deep learning and AI development opportunities in the job market

Top Choice of Leading Companies Worldwide

Industry leaders and professionals globally rely on this top-rated course to enhance their skills.

Course Description

This course offers a deep dive into an advanced neural network construction – convolutional neural networks. First, we explain the concept of image kernels, and how it relates to CNNs. Then, you will get familiar with the CNN itself, its building blocks, and what makes this kind of network necessary for computer vision. You’ll apply the theoretical bit to the MNIST example using TensorFlow, and understand how to track and visualize useful metrics using TensorBoard in a dedicated practical section. Later in the course, you’ll be introduced to a handful of techniques to improve the performance of neural networks, and a huge real-world practical project for classifying fashion item pictures. Finally, we will cap it all off with an intriguing look through the history of the most influential CNN architectures.

Learn for Free

What does the course cover?

1.1 What does the course cover?

6 min

Why CNNs?

1.2 Why CNNs?

4 min

Introduction to image kernels

2.1 Introduction to image kernels

3 min

How do image transformations work?

2.2 How do image transformations work?

7 min

Kernels as matrices

2.3 Kernels as matrices

2 min

Convolution - applying kernels

2.4 Convolution - applying kernels

2 min

Curriculum

  • 1. Introduction to the course
    2 Lessons 10 Min

    In this first section, we discuss the topics covered throughout this course along with the numerous benefits of learning about Convolutional Neural Networks.

    What does the course cover?
    6 min
    Why CNNs?
    4 min
  • 2. Kernels
    5 Lessons 17 Min

    Here, we introduce the concept of image kernels and transformations. We will explain how they work through convolution, which forms the basis for CNNs.

    Introduction to image kernels
    3 min
    How do image transformations work?
    7 min
    Kernels as matrices
    2 min
    Convolution - applying kernels
    2 min
    Edge handling
    3 min
  • 3. CNN Introduction
    4 Lessons 23 Min

    This is where we have an in-depth discussion of the Convolutional Neural Networks: you will understand the motivation and fundamental strength of this type of network and learn more about the concepts and layers that make it work – feature maps and pooling layers. Finally, you will discover how the dimensions change in such a network.

    CNNs motivation
    7 min
    Feature maps
    7 min
    Pooling and Stride
    6 min
    Dimensions
    3 min
  • 4. Neural network techniques (revision)
    3 Lessons 9 Min

    In this section, we quickly revise the main concepts of neural networks in general. These include activation functions, overfitting and early stopping, and optimizers. This part is intended only as a reference and is not a substitute for a full course on the basics of Machine Learning.

    Activation functions
    4 min
    Overfitting and early stopping
    2 min
    Optimizers
    3 min
  • 5. Setting up the environment
    2 Lessons 3 Min

    In this part of the course, you will learn how to set up Python 3 and load up Jupyter. We’ll also show you what the Anaconda Prompt is and how you can use it to download and import new modules.

    Setting up the environment - Do not skip, please! Read now
    1 min
    Installing the packages
    2 min
  • 6. CNN assembling - MNIST
    6 Lessons 46 Min

    In this section, you will put theory into practice. You will develop a simple CNN architecture, implement it from scratch, and train the model on the MNIST example.

    Road plan
    3 min
    A simple CNN architecture
    11 min
    Preprocessing the data
    12 min
    Building and training the CNN
    14 min
    MNIST CNN Homework Read now
    1 min
    Testing the trained CNN
    5 min
  • 7. Tensorboard: Visualization tool for TensorFlow
    5 Lessons 38 Min

    After training a model to classify digits, we turn our attention to tracking and visualizing different metrics. The ability to analyze your models is crucial in Machine Learning, and here, we will lay the groundwork which makes that possible through TensorBoard.

    Tensorboard on the MNIST example
    12 min
    Confusion matrix and visualizing it with Tensorboard
    14 min
    Confusion Matrix Homework Read now
    1 min
    Using Tensorboard to tune hyperparameters
    10 min
    Hyperparameter Tuning Homework Read now
    1 min
  • 8. Common techniques for better performance of neural networks
    5 Lessons 19 Min

    This section introduces 3 crucial concepts for improving the performance of neural networks in general. We will discuss theoretically L2 regularization and weight decay, Dropout, and Data Augmentation, which you will practice in the next section.

    Introduction
    2 min
    Regularization
    5 min
    L2 Regularization and weight decay
    5 min
    Dropout
    3 min
    Data augmentation
    4 min
  • 9. A practical project: Labelling fashion items
    16 Lessons 82 Min

    So far, you have already gained some practice with CNNs in a somewhat sterile environment. However, the real world is much messier than the MNIST example. That’s why, in this section, we have prepared a huge practical example inspired by tasks you are very likely to do in your job. You will practice classifying clothes and other fashion items with multiple labels. Here, you will see why the neat results from the MNIST example are almost unattainable and gain valuable insight into the procedure of undertaking such a project.

    Introduction to the problem
    3 min
    The objective and the images
    4 min
    Converting images to arrays
    4 min
    Getting started with the code concepts
    3 min
    Primary classification task - Part 1
    6 min
    Primary classification task - Part 2
    10 min
    Primary classification task - Part 3
    5 min
    Glasses and Sunglasses Homework Read now
    1 min
    Trousers and Jeans - discussion of approaches
    5 min
    Trousers and Jeans - All
    11 min
    Trousers and Jeans - Gender + Type
    4 min
    Trousers and Jeans - Type - Homework Read now
    1 min
    Shoes Homework Read now
    1 min
    Trousers and Jeans - comparing the methods
    8 min
    L2 regularization and Dropout
    11 min
    Data augmentation - Shoes All
    5 min
  • 10. Understanding CNNs
    1 Lesson 7 Min

    In this section, we briefly discuss what aspects of neural networks you need to be careful with, illustrating them with real examples of models that exhibit unexpected behavior.

    Unexpected failures
    7 min
  • 11. Popular CNN architectures
    5 Lessons 19 Min

    This section is dedicated to exploring the most influential and breakthrough Convolutional Neural Networks of the past - AlexNet, VGG, GoogLeNet, and ResNet - and explaining the concepts behind their architectures. We will also look at the Computer Vision competition ILSVRC and its development over the years.

    Introduction - the ILSVRC challenge
    1 min
    AlexNet - CNN success
    3 min
    VGG - more layers
    3 min
    GoogleNet - computational efficiency
    7 min
    ResNet - revolution of depth
    5 min

Topics

TheoryPythonProgrammingmachine learningDeep LearningNeural NetworksComputer VisionTensorflowTensorboardConvolutional Neural NetworksImage Processing

Tools & Technologies

python

Course Requirements

  • You need to complete an introduction to Python before taking this course
  • Basic skills in statistics, probability, and linear algebra are required
  • It is highly recommended to take the Machine Learning in Python and Deep Learning with TensorFlow courses first
  • You will need to install the Anaconda package, which includes Jupyter Notebook

Who Should Take This Course?

Level of difficulty: Advanced

  • Aspiring data scientists, ML engineers, and AI developers
  • Existing data scientists, ML engineers, and AI developers who want to improve their technical skills

Exams and Certification

A 365 Data Science Course Certificate is an excellent addition to your LinkedIn profile—demonstrating your expertise and willingness to go the extra mile to accomplish your goals.

Exams and certification

Meet Your Instructor

Nikola Pulev

Nikola Pulev

Course Creator at

6 Courses

1363 Reviews

21860 Students

Nikola Pulev is a Natural Sciences graduate from the University of Cambridge (UK) turned data science practitioner and a course instructor at 365 Data Science. Nikola has a strong passion for mathematics, physics, and programming. Over the years, he has taken part in multiple national and international competitions, where he has won numerous awards. One of Nikola’s most notable achievements so far is his silver medal from the International Physics Olympiad.

What Our Learners Say

365 Data Science Is Featured at

Our top-rated courses are trusted by business worldwide.

Recommended Courses