Description
Some Student Reviews:
"5/5 stars to Mauricio!
" (March 2018).
"The implementation part is very good and up-too the mark. The explanation step by step process is very good."
(February 2018).
"course done very well; everything is explained in detail; really satisfied !!!"
(February 2018).
"Difficult topics are simply illustrated and therefore easy to understand."
(January 2018).
"So far the course is good, clearly Explanation.
" (November 2017).
═════════════════════════════════════════════════════
***Read the
Quick FAQ
for the entire course lowdown!***
══
═══════════════════════════════════════════════════
NEW
: Final Assignment submission lecture! Send in your CNN app and I'll review it!
NEW:
Trophy Awards for Key Section Achievements!
BONUS
: Artificial
Neural Networks Summary
(for your Review and refreshment)
═════════════════════════════════════════════════════
Hi.
As always, thanks for showing interest in this course!
What makes this course special:
Convolutional Neural Networks (CNN): Concepts, Visual Examples and Presentations
Step-by-Step CNN Creation and Training
Create your CNN application using your own Images
Plus, personalized feedback and help.
You ask, I answer directly!
✅ First:
You'll start with the Neural Networks
Review:
Quickly learn/refresh all about Neural Networks (NNs): Feed-Forward Passes, Gradient Descent and Backpropagation,
Refresh your memory about how NNs learn from data,
After this, you will be ready and set to tackle
Convolutional Neural Networks.
✅ Second:
You'll start your Convolutional Neural Networks endeavor by reviewing their history and motivation:
Why are they so good at prediction?
What makes them so special?
What were the first attempts?
✅ Third:
You'll continue your Convolutional Neural Networks endeavor by going into all required concepts:
How does Convolutional Neural Networks read images?
What's a Convolution layer and how to interpret it?
What are the main components of Convolutional Layers?
Then, learn how all Neural Network concepts stack into Convolutional Layers, i.e. activations, losses,
✅ Forth
:
Before jumping into code, you'll see some Convolutional Neural Networks action:
You'll see 2 Convolutional Neural Networks LIVE,
See how they learn right in front of your eyes,
You'll do exactly the same thing in the next sections! So go for it!
✅ Fifth:
You'll code your first Convolutional Neural Networks application:
Code using the famous MNIST dataset,
Easily understand all learnt concepts applied in this section,
Tweak parameters according to your criteria and get a feel about how Convolutional Neural Networks learn from images.
✅ Sixth:
Now it's time for you to code your own Convolutional Neural Networks app with your own images:
We'll use the hydrangea (Kaggle) image dataset competition,
Learn how to "take" images from your PC for your Convolutional Neural Networks app,
Modify the parameters for the best learning process.
✅ Seventh:
Submit your own Convolutional Neural Networks app as the course's Final Assignment:
Get comments on how to make it better
Learn 100% by applying all concepts in this assignment
Optimize for best results
Lastly, you can
post
questions or doubts, and I’ll answer to you personally.
I’ll see you inside,
-M.A. Mauricio M.
Requrirements
Requirements
1. Python +3.0
2. Keras +2.0
3. Your own Images Set (for Final Assignment project)
4. My NN course (Optional, but highly recommended)