machine learning for beginners - neural networks
4.7 (9 ratings)
Instead of using a simple lifetime average, Udemy calculates a course's star rating by considering a number of different factors such as the number of ratings, the age of ratings, and the likelihood of fraudulent ratings.
196 students enrolled
Wishlisted Wishlist

Please confirm that you want to add machine learning for beginners - neural networks to your Wishlist.

Add to Wishlist

machine learning for beginners - neural networks

Create you first neural networks in python - a hands on guide for beginners
4.7 (9 ratings)
Instead of using a simple lifetime average, Udemy calculates a course's star rating by considering a number of different factors such as the number of ratings, the age of ratings, and the likelihood of fraudulent ratings.
196 students enrolled
Created by Daniel We
Last updated 5/2017
English
Current price: $10 Original price: $100 Discount: 90% off
5 hours left at this price!
30-Day Money-Back Guarantee
Includes:
  • 3.5 hours on-demand video
  • 5 Supplemental Resources
  • Full lifetime access
  • Access on mobile and TV
  • Certificate of Completion
What Will I Learn?
  • being able to create your own neural networks in python
  • train and evalute your neural network
  • make predictions with your model
  • being able to leverage scikit learn in combination with keras
  • create convolutional neural networks for image recognition
View Curriculum
Requirements
  • !Please note I reupload all files in a larger size and appended them at the end
  • Install Python and the relevant modules (numpy, keras, tensorflow/theano e.g. via Pip)
  • Being familiar with basic Python syntax
  • This is a hands-on approach and not a university lecture with lots of theory
  • I believe in praxis - so I want you to code with me
  • Note that I use tensorflow 0.12.1 and keras 1.2.2 versions here. Other versions could cause problems since modules and names where changed! To follow here install my versions
  • Theoretical background is certainly helpful and can easily found on wikipedia or other sources
Description

What is machine learning / ai ? How to lean machine learning in practice?

machine learning / ai (artificial intelligence) and neural networks (often referred to as deep learning) are one of the hottest topics in this century - for good reasons.

There are a lot of interested people out there but many do not know where to start. The difficult question basically is how to start actually learning it?

Especially beginners might get discouraged because of statistics and math which is an integral part of machine learning. Also matrix operations in tensorflow are not considered easy peasy. None the less you do not need to be a math expert to apply machine learning. This is my third course to show you why.

Instead of telling you all the statistics and math behind the neural network and deep learning i prefer to give you a much more hands on approach. At the end of the day there's only one thing that really counts - THE RESULT. I believe in a practical approach. That's why the course is developed to encourage you to follow along and write the code yourself. At the end you can see your result.

By joining this course you can leverage the knowledge you acquired from my first two courses (Machine Learning for Beginners and machine learning for beginners - deep dive) and get the chance to dive into theworld of neural networks. Again this course is not for students who like to learn theory. Those should rather turn to a university professor or wikipedia.

But if you want to actually practise machine learning and neural networks with python and tensorflow and learn how to write and improve your own algorithms then this beginner's course is the right way to continue your learning journey!

I wish you all the best, enjoy the course, get your hands dirty and start coding! Let's master neural networks from scratch

See you in the first lecture


In case you want to dive deeper into the theoretical understanding I refer you to my two other courses.

  1. A crash course in neural networks for beginners
  2. A crash course in neural networks for beginners deep dive

These should give you an easy way to understand the different kinds of deep learning nets in less than 2 hours.

Who is the target audience?
  • aspiring personalities who want to enter one of the most hottest topics on this planet with huge future potential
  • beginners in machine learning
  • people who like a hands-on approach and not only watching
  • people who prefer practice instead of theory
Students Who Viewed This Course Also Viewed
Curriculum For This Course
31 Lectures
03:35:04
+
Enter the M. - Hands on approach to develop your own neural network
17 Lectures 01:50:24


Define the structure of our model

Defining your model - how does the structure look like?
09:41

The next step. Model compilation

Next step - compiling the model
04:33

Our model needs training

Training Time
03:58

Cards on the table. What's our model's performance?

Evaluation Time - how is our neural network perfoming?
05:49

Let's make a prediction

Time to predict the future - make predictions with your model
04:28

Combine skicit learn and keras to get the best out of both

Leverage skicit learn with keras - Introduction
01:58

Optimize your neural network to deliver better results

Parameter optimization for your neural network
13:12

What are the best Parameters? Take a look

The Result
00:39

Let's do a regression with our neural network

Neural Network for Regression
14:40

Show me the result!

The Regression result
02:15

At first we visualize our dataset. What are we dealing with?

Let's dive into convolutional neural networks
05:58

We need to preprocess our data in order to feed our neural network

Preprocessing our dataset for our model
14:16

Captions says it all. Let's get into it!

Create,train and evaluate our model
15:09

Let's watch the output of our CNN model

The result
02:00

Alpha and Omega. Let's sum up what you have accomplished

Conclusion and final words
01:43
+
SCREENSIZE ENLARGED!
14 Lectures 01:44:40
Load the dataset
08:01

Defining your model
09:41

Compiling the model
04:33

Training time
03:58

Evaluation Time
05:49

Time to predict the future
04:28

9 Parameter Optimization
13:12

10 The result
00:39

11 Neural Networks for Regression
14:41

12 The Regression result
02:15

13 Let'sdive into CNNs
05:58

14 Preprocessing our dataset for our model
14:16

15 create train and evaluate our model
15:09

16 The result
02:00
About the Instructor
Daniel We
4.6 Average rating
195 Reviews
4,966 Students
19 Courses
Traveller

Daniel is a 28 year old entrepreneur ,data scientist and web analyst consultant. He holds a master degree as well as other major certificates from Google and others.

He is committed to support other people by offering them educational services to help them accomplishing their goals and becomming the best in their profession.

"In order to do the impossible you need to see the invisible"