Comprehensive Guide to Artificial Intelligence(AI) for All

Focused View

Junaid Ahmed

11:19:46

57 View

1 - What is AI and its Impact on our society and future

1 - Quiz 1.html

1 - Resources and Jupyter Notebooks.html

2 - Introduction the course sections.mp4

04:06

2 - Quiz 2.html

3 - Quiz 3.html

3 - What is Artificial Intelligence AI.mp4

02:40

4 - Mapping human functions to AI technologies.mp4

02:40

4 - Quiz 4.html

5 - AI Branches of Machine Learning Algorithms.mp4

03:43

5 - Quiz 5.html

6 - AI Supervised Machine Learning Algorithms and Applications.mp4

04:40

6 - Quiz 6.html

7 - AI Unsupervised Machine Learning Algorithms and Applications.mp4

03:08

8 - AI Natural Language Processing and Applications.mp4

07:59

9 - AI Computer Vision and Applications.mp4

06:31

10 - AI IOT and Applications.mp4

06:26

11 - What are Neural Networks.mp4

02:07

12 - Neural Networks Perceptron.mp4

06:47

13 - What are Deep Neural Networks.mp4

04:52

14 - Feed Forward Neural Networks FFNN Structure and Forward pass.mp4

05:00

15 - Input Feed Forward Neural Networks FFNN.mp4

01:13

16 - Learning Phase Feed Forward Neural Networks FFNN.mp4

09:11

17 - Back propagation and learning step Feed Forward Neural Networks FFNN.mp4

05:27

18 - Applications and Limitations of Feed Forward Neural Networks FFNN.mp4

01:12

19 - CNN Introduction.mp4

02:47

20 - CNN Convolution and Relu Layer.mp4

06:33

21 - CNN Max Pooling Layer.mp4

04:07

22 - CNN Example end to end.mp4

02:39

23 - Recurrent Neural Networks RNN.mp4

04:02

24 - RNN Architecture.mp4

03:20

25 - Generative Adversarial Networks GAN.mp4

03:45

26 - Reinforcement Learning.mp4

05:05

27 - Transfer Learning.mp4

04:14

28 - Market Potential of AI.mp4

03:24

29 - Who will loose to AI.mp4

07:09

30 - Need for retraining and reskilling.mp4

02:50

31 - How to take advantage and benefit from AI.mp4

04:42

32 - References for further study.html

2 - IBM Watson Supervised and Unsupervised Machine Learning Models

33 - Building Supervised and Unsupervised Machine learning Models using IBM Watson.mp4

02:02

33 - Gosalescsv.csv

34 - Approach to building machine learning Models.mp4

05:02

35 - Account Setup and Configuration.mp4

04:15

36 - Supervised Building a Binary classificationML model and Uploading Data.mp4

01:57

37 - Supervised Training and testing your model using logistic regression.mp4

07:40

38 - Supervised Building a Multi class classificationML model end to end.mp4

07:14

39 - Unsupervised Building a RegressiveML Model end to end.mp4

05:12

40 - Performance Evaluation Parameters for ML Algorithms.mp4

06:14

3 - Natural Language Processing NLP with IBM Watson

41 - Introduction to the Section.mp4

01:47

42 - IBM Watson Text to Speech.mp4

06:03

43 - IBM Watson Speech to Text.mp4

05:27

44 - IBM Watson Semantic extraction.mp4

07:32

4 - Feed Forward Neural Networks FFNN with Tensor Flow Simulator and Google Colab

7 - Quiz 7.html

45 - Introduction to the Section and the experiment sheet.mp4

02:28

46 - Building a Perceptron.mp4

03:26

47 - Building a Feed Forward Neural Network with one Hidden layer Supervised.mp4

03:23

48 - Building a Deep Feed Forward Neural Network Supervised.mp4

03:26

49 - High Level Introduction to Tensor Flow Data and Setup Unsupervised.mp4

02:44

50 - Building a Regressive Feed Forward Neural NetworkFFNN Unsupervised.mp4

11:30

51 - Building a SHALLOW Regressive Feed Forward Neural Network Unsupervised.mp4

03:41

52 - Building a DEEP Regressive FFNN Unsupervised.mp4

04:19

53 - Building a Regressive FFNN with different AdamOptimizer.mp4

03:49

54 - Building a Regressive FFNN with different learning Rates and Epochs.mp4

10:10

55 - Performance Analysis of Feed Forward Neural Networks.mp4

06:05

5 - Convolutional Neural Networks CNN with IBM Watson

8 - Quiz 8.html

56 - Section Introduction and data.mp4

03:55

57 - CNN for MNIST Architecture Walkthrough.mp4

01:40

58 - IBM Watson Account Setup Basics.mp4

04:05

59 - CNN Setup and First Run with MNIST example Part 1.mp4

13:00

60 - CNN Setup and First Run with MNIST example Part 2.mp4

09:20

61 - CNN for MNIST with SGD.mp4

06:19

62 - Optimizing CNN for MNIST.mp4

15:58

63 - CNN for CIFAR 10.mp4

12:24

64 - Optimization options for CNN on CIFAR 10.mp4

08:29

65 - CNN Unconverging Experiments.mp4

04:51

6 - Recurrent Neural Network RNN with Mathworks

9 - Quiz 9.html

66 - Introduction the section.mp4

01:25

67 - Japanese Vowels classification with LSTM Walk through of Mathworks example.mp4

11:21

68 - Classification of human activities with LSTM Walk through of Mathworks example.mp4

07:49

7 - Way forward

69 - Introduction to sections below.mp4

03:05

70 - Installation of softwares and libraries for all the sections below.mp4

19:28

8 - Introduction to Python with Jupyter Notebook

71 - Introduction to Python.mp4

01:57

72 - Numbers and Variables.mp4

07:45

73 - Strings and Lists.mp4

14:24

74 - Control Structures.mp4

15:26

75 - Control Structures Part 2.mp4

15:16

76 - Data Structures Part 1.mp4

12:40

77 - Data Structures Part 2.mp4

07:34

78 - Classes Part 1.mp4

07:51

79 - Classes Part 2.mp4

10:01

80 - Io Error Handling and Library Walk through.mp4

16:16

9 - Introduction to Numpy

81 - Introduction and Creating arrays.mp4

07:48

82 - Creating 1D 2D 3D Arrays.mp4

04:51

83 - Creating Dummy Data.mp4

04:14

84 - Reshaping 1D 2D and 3D Arrays.mp4

06:02

85 - Slicing Dicing and Splitting Arrays.mp4

07:24

10 - Introduction to Pandas Matplotlib and OpenCV

86 - Introduction and Data Frames.mp4

08:27

87 - Slicing and Dicing.mp4

08:27

88 - ImportExportcsvexceljsonpickle.mp4

05:56

89 - Basic Plotting with Matplotlib.mp4

12:29

90 - Displaying CIFAR 10 images with Matplotlib.mp4

01:50

91 - Object Recognition Video Analysis and more with OpenCV.mp4

13:48

11 - Working with Keras Advanced Deep Learning

10 - Quiz 10.html

92 - Introduction to Keras.mp4

01:42

93 - Multi Class Classification using a Deep Neural Network with Keras.mp4

12:19

94 - Binary Classification using a Deep Neural Network with Keras.mp4

03:43

95 - Building a VGG16 like Deep Neural Network with Keras.mp4

04:58

96 - Solving MNIST data set using a Deep Neural Network with Keras Part 1.mp4

05:34

97 - Solving MNIST data set using a Deep Neural Network with Keras Part 2.mp4

07:10

98 - Solving MNIST data set using a Deep Neural Network with Keras Part 3.mp4

07:40

99 - Migrating models from IBM Watson to run on local your Jupyter Notebook.mp4

14:11

100 - Building Stateful RNN on Jupyter Notebook.mp4

08:53

12 - Transfer and Reinforcement Learning

11 - Quiz 11.html

101 - Transfer Learning Reusing a Prebuilt ResNet50 Model to Predict.mp4

07:02

102 - Transfer Learning feature extraction from VGG16 Model.mp4

08:07

103 - Transfer Learning Retraining the last layers.mp4

12:48

104 - Reinforcement Learning CartPole Example Part 1.mp4

07:48

105 - Reinforcement Learning CartPole Example Part 2.mp4

05:41

106 - Reinforcement Learning Pendulum Example.mp4

10:50

Description

Learn ML, NLP, Deep, Transfer and Reinforcement learning with IBM Watson, Tensorflow Sim, Keras, OpenAI Gym and more

What You'll Learn?

Clearly define what is AI and Deep Learning
Build Convolutional Neural Network on IBM Watson for MNIST and CIFAR 10 Datasets (No coding)
Build Supervised and Unsupervised Machine learning Models using IBM Watson (No coding)
Test Natural Language Processing (NLP) models using IBM Watson
Build VGG like nets, Stateful RNN nets, reuse ResNet50 using Keras
Test Reinforcement Learning with Keras and OpenAI Gym
Test Recurrent Neural Network (RNN) on Mathworks
Learn to code with Python the easy way
Test Feed Forward Neural Networks(Classification and Regression) on Tensor Flow simulator and Google Colab
Solve popular data sets like MNIST, CIFAR 10, with CNN using Keras
Learn a few useful and important application of popular libraries like Numpy, Pandas, Matplotlib
Migrate Deep Neural Network models from IBM Watson to run on local your Jupyter notebook
Apply Transfer Learning techniques such as Reusing, Retraining with keras
Be able to identify the positive and the negative impact that AI will create

Who is this for?

Folks who are curious about AI and want to learn it, in the fastest, easiest and the most effective way

What You Need to Know?

Basic knowledge of IT, Maths and Data

More details

Description
If I can tell you, stop what ever you are doing and do a certain thing. I would say "Learn about AI and the impact it is going to have in your professional life, personal life and much more in the immediate future".
Welcome to this exciting and eye opening course on Artificial Intelligence and more. We believe that AI will touch everybody in some level, whether you are a technical or a non technical person and also that you can excel in many roles in AI with just a functional understanding of coding.
The course has over 11 hours of content with 100+ easy to consume, high quality, visually engaging, condensed and edited videos, over 10 Quizzes to check your understanding, reference material and code for further study.Â
This course has 3 parts, first we will start from the basics , break myths, clarify your understanding as to what is this mysterious term AI, (many are surprised to know that it encompasses, Machine Learning, NLP,Computer Vision, IOT, Robotics and more). We will also understand the current state of AI and its positive and negative impact in the near future.

Then we will apply the concepts we learnt with zero to little coding Involved.
- Machine learning (Supervised and Unsupervised)Â with IBM Watson
- Natural Language Processing (NLP) with IBM Watson
- Feed Forward Neural Networks (FFNN) with Tensor Flow Simulator
- ConvolutionalÂ Neural Networks with (CNN) with IBM Watson
-Â Recurrent Neural Networks (RNN) with Mathworks

Smack in the middle we have easy and intuitive primer sections on how to code using Python, and also how to use popular libraries like Numpy, Pandas, Matplotlib all on the awesome browser based coding platform Jupyter notebook. These middle sections will prepare you for the next sections.
The final set of sections we will take a deeper dive in testing real life use cases and AIÂ applications with Keras, Keras-Reinforcement, OpenAI Gym and more. The focus will be on building the student's confidence in understanding the data and building solutions. In theÂ final sections you will see a bit more of code but the best part would be that by the end of the sections you will be running AI solutions powered byÂ Deep Neural Networks on a browser with Jupyter Notebook on your Laptop !

- Solving popular data sets likeÂ MNIST, CIFAR 10, with CNN, Keras and Jupyter notebook running on your laptop
- Building VGGÂ like nets and Stateful RNN nets using Keras
- Migrating Neural networks from IBM Watson to run on local your Jupyter notebook
- Applying Transfer Learning technique such as Reusing, Retraining with keras
-Â Testing Reinforcement Learning with Keras and OpenAI Gym

The essence of the later sections will be to understand that there are so many libraries and resources available to you, and that it has been made easy for everyone. You just have to identify what you need to be done and look in the right direction.
AI brings tremendous opportunity like higher economic growth, productivity and prosperity but the picture is not all rosy. lets look at some data points from the renowned Mckinsey&Company.

" 250 million new jobs are likely to be created by 2030"*
" In the midpoint adoption scenario 400 million Jobs are likely to be lost by 2030"*
" In the midpoint adoption scenario 75 million will need change occupational categories by 2030"*

AI is the top priority for Companies, governments and institutions alike. AI surpasses a certain product, or vertical, or function, or a specific industry , it encompasses everything. It is all prevalent.
Based on the report there will be considerable shortages in the ITÂ sector and companies are looking to fill these gaps by retraining, hiring, redeploying, contracting and even hiring from non traditional sources. Technological skill is the TOPÂ skill that will be required during this time and by one research they will need 250,000 data scientists by 2030.Â If you develop these skills and knowledge , you can take advantage of this revolution irrespective of your role, company or Industry you belong to.
So if you are "AIÂ ready then you are future ready"
AIÂ is here to stay and the ones who get on board fast and adapt to it will be in a much better position to face the exciting but uncertain future.
Choose Success , make yourself invaluable and irreplaceable. I will see "YOU" on the inside.
God Speed.

Who this course is for:
Folks who are curious about AI and want to learn it, in the fastest, easiest and the most effective way

User Reviews

Rating

average 0

Total votes0

Focused display

Artificial Intelligence

Junaid Ahmed

Instructor's Courses

Hello there! I am Junaid Ahmed. I have a bachelors in electrical and electronics engineering and a masters in software engineering . I would like to call my self an Innovation technologist, I am excited to learn, Implement and teach new technologies. I come from a background in enterprise software, and I am currently also focusing on Internet of things , AR, AI and Leading an IoT product development. I have experience with enterprise applications, reporting, and security products. I have consulted with large organizations in Government, Telecom, Power, FMCG sectors, and start-ups. I manage projects using agile methods and tools. I hold certifications in SAP HANA and scrum master. As far as training goes I have been involved in it parallelly for the decade in different products and practices including real-time analytics, IoT, AI and AR. I have around 50,000 students enrolled in my courses on Udemy. Our clients include Consulting Companies, Implementation partners, Consultants and anybody who is eager to learn in the best way possible. Happy Learning!

Udemy

View courses Udemy

Students take courses primarily to improve job-related skills.Some courses generate credit toward technical certification. Udemy has made a special effort to attract corporate trainers seeking to create coursework for employees of their company.