CF

Deep Learning A-Z™: Hands-On Artificial Neural Networks

22h 36m 30s
English
Paid

Artificial intelligence is growing exponentially, impacting numerous fields and industries. From self-driving cars amassing millions of miles to IBM Watson diagnosing patients more accurately than teams of doctors, and Google DeepMind's AlphaGo defeating the world champion at Go—AI is reimagining the boundaries of technology.

Course Overview

As AI continues to advance, the complexity of the problems it addresses also increases. Deep Learning is at the heart of Artificial Intelligence, providing solutions to these complex challenges.

Why Choose Deep Learning A-Z™?

Discover five key reasons why Deep Learning A-Z™ stands out among other training programs:

  1. Robust Structure: The course is structured into two volumes - Supervised and Unsupervised Deep Learning, each focusing on three key algorithms, providing a comprehensive understanding of Deep Learning.
  2. Intuition Tutorials: Unlike other courses, we emphasize understanding the rationale behind Deep Learning algorithms, developing an intuitive grasp before delving into theory or coding.
  3. Exciting Projects: Work with Real-World datasets to solve actual business problems, avoiding outdated data sets. Projects include challenges in customer churn, image recognition, stock price predictions, fraud detection, and recommender systems.
  4. Hands-On Coding: Learn by coding from scratch with step-by-step guidance, making the course practical and directly applicable to your projects.
  5. In-Course Support: Access our team of Data Scientists ready to assist with any questions within 48 hours, ensuring continuous learning support.

Tools Covered

Gain proficiency in the most popular tools for Deep Learning:

Tensorflow and PyTorch

These open-source libraries are core to Deep Learning. You'll learn when to use each and how they compare, gaining practical experience in both.

Additional Tools

  • Theano: Similar to Tensorflow, it provides a powerful deep learning foundation.
  • Keras: A high-level API simplifying the implementation of Deep Learning models through concise code.
  • Scikit-learn: Essential for model evaluation, parameter tuning, and data preprocessing.

Enhance your Python skills using libraries such as Numpy, Matplotlib, and Pandas for comprehensive data manipulation and visualization.

Who Is This Course For?

This course is perfect for:

  • Beginners wanting an accessible introduction to Deep Learning without being overwhelmed by programming or math complexities.
  • Experienced individuals seeking to master cutting-edge Deep Learning algorithms and gain hands-on experience with real-world challenges.
  • Data analysts, students, business owners, or anyone interested in leveraging Deep Learning for their career or business.

Real-World Case Studies

Apply your knowledge in the following real-world scenarios:

  • Churn Modelling Problem: Predict customer attrition using Artificial Neural Networks.
  • Image Recognition: Build Convolutional Neural Networks to identify objects in images.
  • Stock Price Prediction: Utilize Recurrent Neural Networks for predicting stock market trends.
  • Fraud Detection: Detect fraudulent credit card applications using Unsupervised models.
  • Recommender Systems: Develop systems to suggest movies or products, improving customer experience.

Course Requirements

  • High school-level mathematics
  • Basic knowledge of Python programming

What You'll Learn

  • Understand and implement various Neural Networks, including Artificial, Convolutional, Recurrent, Self-Organizing Maps, Boltzmann Machines, and AutoEncoders.

About the Author: Udemy

Udemy thumbnail

Udemy is the largest open marketplace for online courses on the internet. Founded in 2010 by Eren Bali, Oktay Caglar, and Gagan Biyani and headquartered in San Francisco, the company went public on the Nasdaq in 2021 under the ticker UDMY. The platform hosts well over two hundred thousand courses across software development, IT and cloud, data science, design, business, marketing, and creative skills, taught by tens of thousands of independent instructors. Roughly seventy million learners use it worldwide, and the corporate arm — Udemy Business — supplies a curated subset of that catalog to enterprise customers.

Because Udemy is a marketplace rather than a single editorial publisher, the catalog is uneven by design. The strongest material lives in the long-form, project-based courses authored by working engineers — full-stack JavaScript, React, Node.js, Python data science, AWS, Docker and Kubernetes, mobile development with Flutter and React Native, and cloud certification preparation. The CourseFlix listing under this source is the slice of that catalog that has been mirrored here for offline-friendly viewing, organized by topic and updated as new releases land. Pricing on Udemy itself swings dramatically with the site's near-permanent sales, which is why the platform is best treated as a deep reference catalog: pick instructors with strong reviews and a track record of updating their material rather than buying on the headline price alone.

Watch Online 155 lessons

This is a demo lesson (10:00 remaining)

You can watch up to 10 minutes for free. Subscribe to unlock all 155 lessons in this course and access 10,000+ hours of premium content across all courses.

View Pricing
0:00
/
#1: Updates on Udemy Reviews
All Course Lessons (155)
#Lesson TitleDurationAccess
1
Updates on Udemy Reviews Demo
02:58
2
What is Deep Learning?
12:35
3
Installing Python
07:28
4
How to get the dataset
01:33
5
Plan of Attack
02:53
6
The Neuron
16:16
7
The Activation Function
08:30
8
How do Neural Networks work?
12:49
9
How do Neural Networks learn?
13:00
10
Gradient Descent
10:14
11
Stochastic Gradient Descent
08:45
12
Backpropagation
05:23
13
How to get the dataset
01:33
14
Business Problem Description
05:00
15
Building an ANN - Step 1
12:41
16
Building an ANN - Step 2
17:17
17
Building an ANN - Step 3
03:15
18
Building an ANN - Step 4
02:22
19
Building an ANN - Step 5
12:21
20
Building an ANN - Step 6
02:44
21
Building an ANN - Step 7
03:33
22
Building an ANN - Step 8
06:56
23
Building an ANN - Step 9
06:22
24
Building an ANN - Step 10
06:54
25
Homework Solution
13:04
26
Evaluating the ANN
19:36
27
Improving the ANN
07:25
28
Tuning the ANN
19:41
29
Plan of attack
03:32
30
What are convolutional neural networks?
15:50
31
Step 1 - Convolution Operation
16:39
32
Step 1(b) - ReLU Layer
06:42
33
Step 2 - Pooling
14:14
34
Step 3 - Flattening
01:53
35
Step 4 - Full Connection
19:26
36
Summary
04:20
37
Softmax & Cross-Entropy
18:21
38
How to get the dataset
01:33
39
Introduction to CNNs
04:09
40
Building a CNN - Step 1
09:31
41
Building a CNN - Step 2
03:01
42
Building a CNN - Step 3
01:06
43
Building a CNN - Step 4
12:52
44
Building a CNN - Step 5
04:59
45
Building a CNN - Step 6
05:00
46
Building a CNN - Step 7
05:50
47
Building a CNN - Step 8
02:50
48
Building a CNN - Step 9
19:46
49
Building a CNN - Step 10
08:26
50
Homework Solution
16:05
51
Plan of attack
02:33
52
The idea behind Recurrent Neural Networks
16:03
53
The Vanishing Gradient Problem
14:28
54
LSTMs
19:48
55
Practical intuition
15:12
56
EXTRA: LSTM Variations
03:38
57
How to get the dataset
01:33
58
Building a RNN - Step 1
06:30
59
Building a RNN - Step 2
07:05
60
Building a RNN - Step 3
05:58
61
Building a RNN - Step 4
14:24
62
Building a RNN - Step 5
10:41
63
Building a RNN - Step 6
02:51
64
Building a RNN - Step 7
08:43
65
Building a RNN - Step 8
05:21
66
Building a RNN - Step 9
03:21
67
Building a RNN - Step 10
04:22
68
Building a RNN - Step 11
10:32
69
Building a RNN - Step 12
05:23
70
Building a RNN - Step 13
16:51
71
Building a RNN - Step 14
08:16
72
Building a RNN - Step 15
09:37
73
Plan of attack
03:11
74
How do Self-Organizing Maps Work?
08:31
75
Why revisit K-Means?
02:20
76
K-Means Clustering (Refresher)
14:18
77
How do Self-Organizing Maps Learn? (Part 1)
14:25
78
How do Self-Organizing Maps Learn? (Part 2)
09:38
79
Live SOM example
04:29
80
Reading an Advanced SOM
14:27
81
EXTRA: K-means Clustering (part 2)
07:49
82
EXTRA: K-means Clustering (part 3)
11:52
83
How to get the dataset
01:33
84
Building a SOM - Step 1
13:43
85
Building a SOM - Step 2
09:40
86
Building a SOM - Step 3
17:26
87
Building a SOM - Step 4
11:13
88
Mega Case Study - Step 1
02:50
89
Mega Case Study - Step 2
04:17
90
Mega Case Study - Step 3
14:38
91
Mega Case Study - Step 4
09:03
92
Plan of attack
02:25
93
Boltzmann Machine
14:23
94
Energy-Based Models (EBM)
10:40
95
Editing Wikipedia - Our Contribution to the World
03:29
96
Restricted Boltzmann Machine
17:30
97
Contrastive Divergence
16:29
98
Deep Belief Networks
05:24
99
Deep Boltzmann Machines
02:58
100
How to get the dataset
01:33
101
Building a Boltzmann Machine - Introduction
09:10
102
Building a Boltzmann Machine - Step 1
09:14
103
Building a Boltzmann Machine - Step 2
09:41
104
Building a Boltzmann Machine - Step 3
08:22
105
Building a Boltzmann Machine - Step 4
20:54
106
Building a Boltzmann Machine - Step 5
05:06
107
Building a Boltzmann Machine - Step 6
07:34
108
Building a Boltzmann Machine - Step 7
10:14
109
Building a Boltzmann Machine - Step 8
12:37
110
Building a Boltzmann Machine - Step 9
06:18
111
Building a Boltzmann Machine - Step 10
11:35
112
Building a Boltzmann Machine - Step 11
06:58
113
Building a Boltzmann Machine - Step 12
13:24
114
Building a Boltzmann Machine - Step 13
18:43
115
Building a Boltzmann Machine - Step 14
17:11
116
Plan of attack
02:13
117
Auto Encoders
10:51
118
A Note on Biases
01:16
119
Training an Auto Encoder
06:11
120
Overcomplete hidden layers
03:53
121
Sparse Autoencoders
06:16
122
Denoising Autoencoders
02:33
123
Contractive Autoencoders
02:24
124
Stacked Autoencoders
01:55
125
Deep Autoencoders
01:51
126
How to get the dataset
01:33
127
Building an AutoEncoder - Step 1
12:05
128
Building an AutoEncoder - Step 2
11:50
129
Building an AutoEncoder - Step 3
08:22
130
Building an AutoEncoder - Step 4
20:52
131
Building an AutoEncoder - Step 5
05:05
132
Building an AutoEncoder - Step 6
16:46
133
Building an AutoEncoder - Step 7
13:38
134
Building an AutoEncoder - Step 8
15:06
135
Building an AutoEncoder - Step 9
13:33
136
Building an AutoEncoder - Step 10
04:23
137
Building an AutoEncoder - Step 11
11:27
138
THANK YOU bonus video
02:41
139
Simple Linear Regression Intuition - Step 1
05:46
140
Simple Linear Regression Intuition - Step 2
03:10
141
Multiple Linear Regression Intuition
01:04
142
Logistic Regression Intuition
17:08
143
Data Preprocessing - Step 1
07:26
144
Data Preprocessing - Step 2
07:55
145
Data Preprocessing - Step 3
10:40
146
Data Preprocessing - Step 4
12:58
147
Data Preprocessing - Step 5
10:41
148
Data Preprocessing - Step 6
10:50
149
Data Preprocessing Template
03:42
150
Logistic Regression Implementation - Step 1
05:22
151
Logistic Regression Implementation - Step 2
03:22
152
Logistic Regression Implementation - Step 3
02:35
153
Logistic Regression Implementation - Step 4
04:14
154
Logistic Regression Implementation - Step 5
19:35
155
Classification Template
03:40
Unlock unlimited learning

Get instant access to all 154 lessons in this course, plus thousands of other premium courses. One subscription, unlimited knowledge.

Learn more about subscription

Related courses

Frequently asked questions

What are the prerequisites for enrolling in this course?
The course requires a basic understanding of Python, as the initial lessons include installing Python and coding from scratch. Familiarity with basic mathematical concepts, such as calculus and linear algebra, would be beneficial due to topics like gradient descent and backpropagation. However, the course offers intuition tutorials to help develop a strong conceptual foundation before diving into technical details.
What projects will I work on during the course?
The course features several real-world projects, allowing you to apply deep learning techniques to business problems. Key projects include customer churn prediction, image recognition, stock price prediction, fraud detection, and developing recommender systems. These projects involve working with up-to-date datasets, ensuring practical and relevant learning experiences.
Who is the target audience for this course?
This course is aimed at individuals interested in artificial intelligence and deep learning, including data scientists, machine learning practitioners, and software developers. It is suitable for those looking to build a solid foundation in both supervised and unsupervised deep learning while working on practical projects to enhance their skills.
What specific deep learning algorithms are covered?
The course provides a comprehensive understanding of both supervised and unsupervised deep learning algorithms. Specific algorithms covered include artificial neural networks (ANNs), convolutional neural networks (CNNs), and recurrent neural networks (RNNs). Each type of network is explored through detailed step-by-step guidance, intuitive tutorials, and practical coding exercises.
What topics are not covered in this course?
While this course offers a robust introduction to deep learning, it does not cover advanced topics such as generative adversarial networks (GANs), reinforcement learning, or transfer learning in depth. The focus remains on developing strong foundational skills in supervised and unsupervised algorithms through hands-on projects.
How much time will I need to complete the course?
The course consists of 155 lessons. The time commitment will vary based on individual learning pace and experience with programming and mathematical concepts. It is structured to allow learners to progress at their own speed, with intuitive tutorials and practical projects enhancing understanding and retention.
How does the knowledge gained in this course benefit future learning or career opportunities?
The skills acquired from this course provide a strong foundation in deep learning, applicable to various AI and machine learning roles. Understanding neural networks, CNNs, and RNNs is crucial for tackling complex challenges in industries like healthcare, finance, and technology. This knowledge also serves as a stepping stone for advanced AI courses or research.