365DataScience
365DataScience Logo

Convolutional Neural Networks with TensorFlow in Python 

  • Offered by365DataScience

Convolutional Neural Networks with TensorFlow in Python
 at 
365DataScience 
Overview

Introducing you to the fundamentals of convolutional neural networks (CNNs) and computer vision

Duration

4 hours

Mode of learning

Online

Credential

Certificate

Convolutional Neural Networks with TensorFlow in Python
 at 
365DataScience 
Highlights

  • Earn a certificate from 365 Data Science
  • Learn from 48 High Quality Lessons
  • Gain access to 8 practical asks
Details Icon

Convolutional Neural Networks with TensorFlow in Python
 at 
365DataScience 
Course details

What are the course deliverables?
  • Learn the fundamentals of CNNs
  • Get the hang of convolution
  • Perform computer vision
  • Master working with TensorFlow and Tensorboard
  • Approach multilabel classification
  • Understand kernels
More about this course
  • This course offers a deep dive into an advanced neural network construction -convolutional neural networks
  • First, the program explains the concept of image kernels, and how it relates to CNNs
  • Then, students will get familiar with the CNN itself, its building blocks, and what makes this kind of network necessary for computer vision
  • Students will 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, students will 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, students will cap it all off with an intriguing look through the history of the most influential CNN architectures
Read more

Convolutional Neural Networks with TensorFlow in Python
 at 
365DataScience 
Curriculum

Introduction To The Course

What does the course cover?

Why CNNs?

Kernels

Introduction to image kernels

How do image transformations work?

Kernels as matrices

Convolution - applying kernels

Edge handling

CNN Introduction

CNNs motivation

Feature maps

Pooling and Stride

Dimensions

Neural Network Techniques (Revision)

Activation functions

Overfitting and early stopping

Optimizers

Setting Up The Environment

Setting up the environment - Do not skip, please!

Installing the packages

CNN Assembling - MNIST

Road plan

A simple CNN architecture

Preprocessing the data

Building and training the CNN

Testing the trained CNN

Tensorboard: Visualization Tool For TensorFlow

Common Techniques For Better Performance Of Neural Networks

A Practical Project: Labelling Fashion Items

Other courses offered by 365DataScience

– / –
11 hours
– / –
– / –
5 hours
– / –
– / –
4 hours
– / –
– / –
2 hours
– / –
View Other 8 CoursesRight Arrow Icon
qna

Convolutional Neural Networks with TensorFlow in Python
 at 
365DataScience 

Student Forum

chatAnything you would want to ask experts?
Write here...