beginner to advanced - machine learning and neural networks
3.9 (6 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.
182 students enrolled
Wishlisted Wishlist

Please confirm that you want to add beginner to advanced - machine learning and neural networks to your Wishlist.

Add to Wishlist

beginner to advanced - machine learning and neural networks

A special extended crashcourse in machine learning and deep neural networks
New
3.9 (6 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.
182 students enrolled
Created by Daniel We
Last updated 9/2017
English
Current price: $10 Original price: $200 Discount: 95% off
5 hours left at this price!
30-Day Money-Back Guarantee
Includes:
  • 10 hours on-demand video
  • 1 Article
  • 1 Supplemental Resource
  • Full lifetime access
  • Access on mobile and TV
  • Certificate of Completion
What Will I Learn?
  • In depth knowledge about machine learning
  • You know the most important language terms
  • You know the “5 Step Process“ in machine learning
  • You have a variety of different algorithms in your toolbox
  • You know how to deal with data issues
  • You know how to preprocess data and how to select the best features
  • You know how ensemble methods work and how to apply them
  • You know how to improve your algorithm‘s result
  • You know how to automate coding steps
  • You acquired in depth understanding about the structure of various neural network types
  • You know exactly what deep learning is
  • You can implement neural networks in code
  • You know how to combine all this knowlege to solve Classification and Regression Problems
View Curriculum
Requirements
  • Basic knowledge in python is helpful
  • Your personal interest and commitment
  • An open mindset
Description
  1. What is machine learning / ai (artificial intelligence) ? 
  2. How to apply and learn machine learning in practice ? 
  3. What are neural networks ? 
  4. What is deep learning ? 
  5. What kind of neural networks exist ?
  6. What are multilayer perceptrons , what are convolutional neural networks ? How do cnns work ?
  7. What are recurrent neural networks ( rnn ) , what are long short term neural networks ( lstm ) and how do the work?

If you need answers to one or more of these questions, you have come to the right place!

Machine learning and neural networks are the hottest topic out there. Self driving cars, image recognition, ecommerce, predicting customer behavior, stock market predictions, you name it!

Google, Facebook, Tesla, Amazon, Alibaba,... all great companies are working on this topic.

machine learning and neural networks are everywhere and will determine the world of tomorrow. Because of that we all should familiarize ourselves with this topic. If we do so, we will create tremendous opportunities and lay the foundation to a bright future.

Especially as a beginner, it's difficult to get into machine learning and neural networks and there are a lot of questions to ask. Because of that I created this new in depth course to help you get started and equip you with all knowlege you require to go from beginner to advanced. This course provides you with more than 10 hours of highly valuable content. Together we address theory as well as apply this knowlege in practice because only applied knowlege is real knowledge.

Together we will apply various machine learning algorithms and deep learning neural networks in practice. All other resources you need to follow along can be acquired for free and will be shown at the beginning of the couse.

After finishing the course you have acquired a solid foundation which you could leverage in your future career.

Let's get into it.

Who is the target audience?
  • beginners with no prior knowlege
  • beginners who have acquired some knowledge
  • students who are interested in a data science career
Compare to Other Machine Learning Courses
Curriculum For This Course
73 Lectures
10:13:53
+
beginner to advanced - master machine learning and deep learning neural networks
5 Lectures 32:51

you find the indians diabetes dataset to download as a csv file. In case you do not want to directly use an internet connection in the later coding challenges. Happy coding.

Preview 15:53


supervised vs unsupervised machine learning
05:28

machine learning challenges
05:01
+
learn and apply various machine learning algorithms
6 Lectures 57:12

6 Your first machine learning algorithm
14:18

7 Learn machine learning algorithms
05:59

8 Learn various machine learning algorithms
09:07

9 Learn to apply various machine learning algorithms
15:14

10 Learn to apply various machine learning algorithms
07:08
+
Feature Selection and Preprocessing
13 Lectures 01:46:19
11 How to select the right data
13:51

12 Which are the best features to use
08:01

13 Which are the best features to use
07:06

14 Additional feature selection techniques
10:16

15 Additional featue selection techniques
04:53

16 A feature selection case study
21:39

17 Preprocessing Introduction
00:52

18 Preprocessing Scaling Techniques
07:58

19 Preprocessing Scaling Techniques
05:04

20 How to preprocess your data
04:49

21 How to scale your data
04:44

22 Feature Scaling Final Project
15:36

23 A quick recap - when to use what
01:30
+
Which Algorithms perform best
8 Lectures 45:14
24 Highly skilled machine learning algorithms
06:14

25 Bagging Decision Trees
09:02

26 The power of ensembles
02:22

27 Random Forest Ensemble technique
06:31

28 A third ensemble technique
03:55

29 Boosting - Adaboost
04:19

30 boosting esemble stochastic gradient boosting
03:58

31 A final ensemble technique to use
08:53
+
Advanced techniques in machine learning
11 Lectures 01:40:01
32 Q&A Training,validation,testing datasets
05:15

33 Model selection cross validation score
15:36

34 Introduction Model Tuning
01:59

35 Parameter Tuning GridSearchCV
10:14

36 A second method to tune your algorithm
09:34

37 How to automate machine learning
14:27

38 machine learning automation part 2
12:25

39 The 5 step machine learning process
07:42

40 The 5 step machine learning process
05:09

41 Which ML algo should you choose
01:28

42 How to compare machine learning algorithms in practice
16:12
+
Neural Networks and deep learning
30 Lectures 04:32:15
43 Neural Networks introduction
19:11

44 What is deep learning
02:20

45 What is one hot encoding
03:39

46 How to implement one hot encoding
11:46

47 How to implement on hot encoding 2
05:13

48 How to handle missing values intro
07:16

49 missing values to NaNs
12:00

50 How to impute missing values
10:43

51 Introducing the MNIST dataset
05:47

52 Programming a neural network in tensorflow
17:45

53 Programming a neural network - multilayer perceptron in tensorflow 2
12:56

54 Programming a neural network - multilayer perceptron in tensorflow 3
15:43

55 Programming a neural network - multilayer perceptron in tensorflow 4
03:23

56 Introducing keras - a convient way to code neural networks
15:41

57 Introducing keras - a convient way to code neural networks 2
14:08

58 Introducing keras - a convient way to code neural networks 3
03:21

59 Crash course - what is a convolutional neural network and how does a cnn work
08:24

60 Creating a convolutional neural network from scratch
11:34

61 Creating a convolutional neural network from scratch 2
11:11

62 Creating a convolutional neural network 3
02:04

63 What are RNNs - Crashcourse Introduction to RNNs
11:23

64 recurrent neural networks rnn in python
16:02

65 recurrent neural networks rnn in python 2
07:51

66 recurrent neural networks rnn in python
04:08

67 A crashcourse in LSTMs for beginners - understanding LSTMs
16:25

68 long short term memory neural networks lstm in python
10:21

69 long short term memory neural networks lstm in python
08:24

70 long short term memory neural networks lstm in python
01:01

71 What you have accomplished
02:34

Jupyter Notebook files
00:01
About the Instructor
Daniel We
4.5 Average rating
235 Reviews
5,874 Students
21 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"