Save for later

Deep Learning A-Z™

Name: Deep Learning A-Z™: Hands-On Artificial Neural Networks
Rating: 4.3 (3741 reviews)

As seen on Kickstarter

Artificial intelligence is growing exponentially. There is no doubt about that. Self-driving cars are clocking up millions of miles, IBM Watson is diagnosing patients better than armies of doctors and Google Deepmind's AlphaGo beat the World champion at Go - a game where intuition plays a key role.

But the further AI advances, the more complex become the problems it needs to solve. And only Deep Learning can solve such complex problems and that's why it's at the heart of Artificial intelligence.

Why Deep Learning A-Z?

Here are five reasons we think Deep Learning A-Z™ really is different, and stands out from the crowd of other training programs out there:

1. Deep Learning is very broad and complex and to navigate this maze you need a clear and global vision of it.

That's why we grouped the tutorials into two volumes, representing the two fundamental branches of Deep Learning: Supervised Deep Learning and Unsupervised Deep Learning. With each volume focusing on three distinct algorithms, we found that this is the best structure for mastering Deep Learning.

2... But they forget to explain, perhaps, the most important part: why you are doing what you are doing. And that's how this course is so different. We focus on developing an intuitive *feel* for the concepts behind Deep Learning algorithms.

With our intuition tutorials you will be confident that you understand all the techniques on an instinctive level. And once you proceed to the hands-on coding exercises you will see for yourself how much more meaningful your experience will be. This is a game-changer.

Yes? Well then you're in for a treat.

Inside this class we will work on Real-World datasets, to solve Real-World business problems. (Definitely not the boring iris or digit classification datasets that we see in every course). In this course we will solve six real-world challenges:

Artificial Neural Networks to solve a Customer Churn problem
Convolutional Neural Networks for Image Recognition
Recurrent Neural Networks to predict Stock Prices
Self-Organizing Maps to investigate Fraud
Boltzmann Machines to create a Recomender System
Stacked Autoencoders* to take on the challenge for the Netflix $1 Million prize

*Stacked Autoencoders is a brand new technique in Deep Learning which didn't even exist a couple of years ago. We haven't seen this method explained anywhere else in sufficient depth.

4. HANDS- Every practical tutorial starts with a blank page and we write up the code from scratch. This way you can follow along and understand exactly how the code comes together and what each line means.

In addition, we will purposefully structure the code in such a way so that you can download it and apply it in your own projects. Moreover, we explain step-by-step where and how to modify the code to insert YOUR dataset, to tailor the algorithm to your needs, to get the output that you are after.

This is a course which naturally extends into your career.

5. IN-

Well, this course is different. We are fully committed to making this the most disruptive and powerful Deep Learning course on the planet. With that comes a responsibility to constantly be there when you need our help.

In fact, since we physically also need to eat and sleep we have put together a team of professional Data Scientists to help us out. Whenever you ask a question you will get a response from us within 48 hours maximum.

No matter how complex your query, we will be there. The bottom line is we want you to succeed.

The Tools

Tensorflow and Pytorch are the two most popular open-source libraries for Deep Learning. In this course you will learn both.

TensorFlow was developed by Google and is used in their speech recognition system, in the new google photos product, gmail, google search and much more. Companies using Tensorflow include AirBnb, Airbus, Ebay, Intel, Uber and dozens more.

PyTorch is as just as powerful and is being developed by researchers at Nvidia and leading universities: Stanford, Oxford, ParisTech. Companies using PyTorch include Twitter, Saleforce and Facebook.

So which is better and for what?

Well, in this course you will have an opportunity to work with both and understand when Tensorflow is better and when PyTorch is the way to go. Throughout the tutorials we compare the two and give you tips and ideas on which could work best in certain circumstances.

The interesting thing is that both these libraries are barely over 1 year old. That's what we mean when we say that in this course we teach you the most cutting edge Deep Learning models and techniques.

More Tools

Theano is another open source deep learning library. It's very similar to Tensorflow in its functionality, but nevertheless we will still cover it.

Keras is an incredible library to implement Deep Learning models. It acts as a wrapper for Theano and Tensorflow. Thanks to Keras we can create powerful and complex Deep Learning models with only a few lines of code. This is what will allow you to have a global vision of what you are creating. Everything you make will look so clear and structured thanks to this library, that you will really get the intuition and understanding of what you are doing.

Even More Tools

Scikit-learn the most practical Machine Learning library. We will mainly use it:

to evaluate the performance of our models with the most relevant technique, k-Fold Cross Validation
to improve our models with effective Parameter Tuning
to preprocess our data, so that our models can learn in the best conditions

And of course, we have to mention the usual suspects. This whole course is based on Python and in every single section you will be getting hours and hours of invaluable hands-on practical coding experience.

Plus, throughout the course we will be using Numpy to do high computations and manipulate high dimensional arrays, Matplotlib to plot insightful charts and Pandas to import and manipulate datasets the most efficiently.

Who Is This Course For?

As you can see, there are lots of different tools in the space of Deep Learning and in this course we make sure to show you the most important and most progressive ones so that when you're done with Deep Learning A-Z™ your skills are on the cutting edge of today's technology.

If you are just starting out into Deep Learning, then you will find this course extremely useful. Deep Learning A-Z™ is structured around special coding blueprint approaches meaning that you won't get bogged down in unnecessary programming or mathematical complexities and instead you will be applying Deep Learning techniques from very early on in the course. You will build your knowledge from the ground up and you will see how with every tutorial you are getting more and more confident.

If you already have experience with Deep Learning, you will find this course refreshing, inspiring and very practical. Inside Deep Learning A-Z™ you will master some of the most cutting-edge Deep Learning algorithms and techniques (some of which didn't even exist a year ago) and through this course you will gain an immense amount of valuable hands-on experience with real-world business challenges. Plus, inside you will find inspiration to explore new Deep Learning skills and applications.

Real-World Case Studies

Mastering Deep Learning is not just about knowing the intuition and tools, it's also about being able to apply these models to real-world scenarios and derive actual measurable results for the business or project. That's why in this course we are introducing six exciting challenges:

#1 Churn Modelling Problem

In this part you will be solving a data analytics challenge for a bank. You will be given a dataset with a large sample of the bank's customers. To make this dataset, the bank gathered information such as customer id, credit score, gender, age, tenure, balance, if the customer is active, has a credit card, etc. During a period of 6 months, the bank observed if these customers left or stayed in the bank.

Your goal is to make an Artificial Neural Network that can predict, based on geo-demographical and transactional information given above, if any individual customer will leave the bank or stay (customer churn). Besides, you are asked to rank all the customers of the bank, based on their probability of leaving. To do that, you will need to use the right Deep Learning model, one that is based on a probabilistic approach.

If you succeed in this project, you will create significant added value to the bank. By applying your Deep Learning model the bank may significantly reduce customer churn.

#2 Image Recognition

In this part, you will create a Convolutional Neural Network that is able to detect various objects in images. We will implement this Deep Learning model to recognize a cat or a dog in a set of pictures. However, this model can be reused to detect anything else and we will show you how to do it - by simply changing the pictures in the input folder.

For example, you will be able to train the same model on a set of brain images, to detect if they contain a tumor or not. But if you want to keep it fitted to cats and dogs, then you will literally be able to a take a picture of your cat or your dog, and your model will predict which pet you have. We even tested it out on Hadelin’s dog.

#3 Stock Price Prediction

In this part, you will create one of the most powerful Deep Learning models. We will even go as far as saying that you will create the Deep Learning model closest to “Artificial Intelligence”. Why is that? Because this model will have long-term memory, just like us, humans.

The branch of Deep Learning which facilitates this is Recurrent Neural Networks. Classic RNNs have short memory, and were neither popular nor powerful for this exact reason. But a recent major improvement in Recurrent Neural Networks gave rise to the popularity of LSTMs (Long Short Term Memory RNNs) which has completely changed the playing field. We are extremely excited to include these cutting-edge deep learning methods in our course.

In this part you will learn how to implement this ultra-powerful model, and we will take the challenge to use it to predict the real Google stock price. A similar challenge has already been faced by researchers at Stanford University and we will aim to do at least as good as them.

#4 Fraud Detection

According to a recent report published by Markets & Markets the Fraud Detection and Prevention Market is going to be worth $33.19 Billion USD by 2021. This is a huge industry and the demand for advanced Deep Learning skills is only going to grow. That’s why we have included this case study in the course.

This is the first part of Volume 2 - Unsupervised Deep Learning Models. The business challenge here is about detecting fraud in credit card applications. You will be creating a Deep Learning model for a bank and you are given a dataset that contains information on customers applying for an advanced credit card.

This is the data that customers provided when filling the application form. Your task is to detect potential fraud within these applications. That means that by the end of the challenge, you will literally come up with an explicit list of customers who potentially cheated on their applications.

#5 & 6 Recommender Systems

From Amazon product suggestions to Netflix movie recommendations - good recommender systems are very valuable in today's World. And specialists who can create them are some of the top-paid Data Scientists on the planet.

We will work on a dataset that has exactly the same features as the Netflix dataset: plenty of movies, thousands of users, who have rated the movies they watched. The ratings go from 1 to 5, exactly like in the Netflix dataset, which makes the Recommender System more complex to build than if the ratings were simply “Liked” or “Not Liked”.

Your final Recommender System will be able to predict the ratings of the movies the customers didn’t watch. Accordingly, by ranking the predictions from 5 down to 1, your Deep Learning model will be able to recommend which movies each user should watch. Creating such a powerful Recommender System is quite a challenge so we will give ourselves two shots. Meaning we will build it with two different Deep Learning models.

Our first model will be Deep Belief Networks, complex Boltzmann Machines that will be covered in Part 5. Then our second model will be with the powerful AutoEncoders, my personal favorites. You will appreciate the contrast between their simplicity, and what they are capable of.

And you will even be able to apply it to yourself or your friends. The list of movies will be explicit so you will simply need to rate the movies you already watched, input your ratings in the dataset, execute your model and voila. The Recommender System will tell you exactly which movies you would love one night you if are out of ideas of what to watch on Netflix.

Summary

In conclusion, this is an exciting training program filled with intuition tutorials, practical exercises and real-World case studies.

We are super enthusiastic about Deep Learning and hope to see you inside the class.

Kirill & Hadelin

Get Details and Enroll Now

OpenCourser is an affiliate partner of Udemy and may earn a commission when you buy through our links.

Get a Reminder

Rating	4.3★ based on 3,741 ratings
Length	22.5 total hours
Starts	On Demand (Start anytime)
Cost	$12
From	Udemy
Instructors	Kirill Eremenko, Hadelin de Ponteves, SuperDataScience Team, Ligency I Team, Ligency Team
Download Videos	Only via the Udemy mobile app
Language	English
Subjects	Data Science Business
Tags	Data Science Business Development Data & Analytics

Get a Reminder

Similar Courses

What people are saying

neural network

A good course that covered most of the stuff in deep learning, neural network.

It pretty much covers every thing you need to know about neural networks.

Lectures corresponding to Theory behind different neural networks is very helpful and good.

Informative and expansive information on Artificial Neural Networks.

Neural Networks can be an intimidating topic to get into, and it's great to have this resource that breaks down all the relevant concepts into something that is easy to grasp and follow through.

I love that there are in depth explanations behind each type of artificial neural network instead of just blindly going into coding the networks while still providing a great depth of information during the coding tutorials themselves.

Thank you great match and great course It was nice but next time u coud tell us how to use it with php for example Your one stop shop for neural network and all deep learning, the intuition lectures are always great and Hadelin explains the code really well.

This is a very good overview of the different kinds of neural networks.

So that we can modify the neural network according to the need.

In this case the neural network is trained to perform some kind of moving average, which means that the usage of a neural network will not provide us much additional information.

The best thing about this course is that you don't need any prerequisite knowledge, everything is explained from the basics,one can delve into deep learning and neural networks without any prior knowledge of machine learning.

We haven't yet got into the coding part but I somehow understand the theory now behind neural networks.

Acquired a high-level understanding of different neural networks and how they work.

I feel I am getting to know something about Neural Networks.

neural networks

Yes, I plan on doing my research paper on "Applications of Neural networks" next year.

Has the perfect balance in explaining the theoretical aspects of Artificial Neural Networks and how they can be applied in various scenarios The Python projects are well explained and neatly organized Solid.

it's very interesting course, with useful details, getting me a very good point of view about neural networks.

yes good till now Videos doesnt work... Amazing course I did a neural networks course in 1991 and implemented a simple backprop NN on my Intel 286 based PC.

Without going deep into the mathematical part, intuition videos gave me a good idea of whats going on inside the neural networks.

I never realized how applicable neural networks are to actual data problems.

Can't wait to solve problems at work using neural networks.

This course will serve you as the foundation of Deep Learning and especially Neural Networks.

I would recommend this course to people that would like to start working with neural networks and are not too concerned with mathematics and the basis they work on.

If you want to know more about the specifics of DL algorithms and stuff, you have no choice but to get your hands dirty with it and start reading papers and building neural networks.

I had some (very few) pre knowledge an Artificial neural networks, there for it was not hard to follow the first parts of the course.

This is a great course to get you started in deep learning and exposes the user to a variety of neural networks that are out there.

I have gained great amount of knowledge about different kinds of neural networks.

After months of training, I finally had my Eureka moment at Convolutional Neural Networks - you made it happen!

step by step

very detailed and step by step.

Completo di spiegazioni step by step, e di esercizi a casa.

Step by step slowly.

It has taken me step by step to learn machine learning.

The exposure to a wide range of techniques was most valuable and the step by step code creation with explanations made it even more so.

Overall, I think there are better deep learning courses out there for actually learning the concepts, ie with lots of step by step practical exercises.

I like the "code step by step from scratch" approach, which the instructors' another course, Artificial Intelligence A-Z doesn't have.

Many thanks to Kirill and Hadelin for the amazing step by step explanations!

), it would be better instead of just following step by step in the videos.

It's very usefull and step by step tutorial, i really learned a lot !!

This builds the model step by step and has everything I need all in one place.

Step by step instruction No rush ahead Technologically, the course is amazingly helpful.

Excellent step by step Tutorial.

Step by step instructions, clear presentation and in-depth explanation.

so far so good

So far so good I would pick something more advanced next time Good course.

So far so good.

I feel that the explanation is elaborate and too specific good Basically a review of work I did in the 90's so far J'apprends à comprendre ce que sait que le Deep Learning So far so good.

Great explanations it was pretty good as per my standard So far so good.

dritto al punto, anche se in alcune parti forse va anche troppo velocemente, ma ovviamente non possono sapere a priori il livello delle persone che ascoltano the ideas are easily explained Great intro Amazing So far so good.

Looks good till now Starting is really interesting, its like a movie,lets see how much we are gonna learn,so far so good ok I really really enjoyed this course.

good match So far so good.

I have just finished couples of videos, so far so good.

This course -- so far so good.

So far 5/5 rating course study material provided So far so good.. É muito introdutório, achei os primeiros minutos desnecessários (introduzir a história, gráficos de processamento, etc.)

So far so good, will update when I am further into the course Clear, Succinct Instruction.

So far so good let’s wait for the meat and see if the tutorial holds up Helps understand concepts in simple terms - great use of examples clear intuitive explanation.

So far so good!

Dario Dellavalle So far so good.

data science

Thanks Super Data Science I really appreciated this course.

The course exceeded my expectations in many ways as I got a better overall picture of the Deep Learning world and where it's applicable in Data Science.

As we all know, data science itself is an evolving field, so I would like to see better implementation examples rather than the old and tired use-cases.

innovative way of teaching a complex subject like data science and deep learning Yes it is the best match.

The course is worth for its price just started Its a good one and it will help me very well in every aspect of my data science course The course is very detailed yet easy to understand.

I'll continue on to the Data Science and Computer Vision courses.

Instructors are full of passion about data science, this helped me keep a positive altitude through the whole course.

The practical part though is covered just great, even for newbies in the Data Science.

Nice work Very useful, will definitely take to the next level if you're considering a career in Data Science.

I highly recommend this course after taking the "Machine Learning A-Z™: Hands-On Python & R In Data Science" by these same authors.

I recently have joined their supedatascience.com membership and they have over 30 courses and adding in data science.

in addition, I have been a member of udemy.com for the last 3 years and I bought over 230 courses most of them in programming and data science including All Krill and Hydlan classes.

Im now more enlightened to challenge me more in Data science courses!

I have been into data science from last one year.

machine learning a-z course

Also, quite a lot of the material is copied directly from the machine learning A-Z course so it didnt cover as much new material as I first thought it would, the ANN and CNN sections are the same videos as in the other course, the annex at the end is about 20 videos lifted from that course too, and in there are five videos duplicated between the auto encoder and Boltzmann machine tutorials I have already completed Machine learning and Artificial intelligence and now completed Deep learning.

They introduced me to the world of Machine Learning in their best seller "Hands-On Machine Learning A-Z course in Python and R".

This course is maintaining the quality and pace of learning as was in Machine Learning A-Z course TA's are horrible.

After completing the Machine Learning A-Z course, it seems that this course extends on that in more detail.

Great and recommended course I have just started this course but I have completed the machine learning A-Z course by Kirril Eremenka and my experience in that course is excellent, hoping the same experience in this course.

Glad I took the Machine Learning A-Z course, though, or I would have been totally lost.

Finally there is a lot of reuse of Machine Learning A-Z course.

As I also took the Machine Learning A-Z course, I found repetitions on ann, classification and regression topics on this deep learning course.

That's roughly 1/3 of entire value) of the course was just a carbon copy repeat of what was already taught in the Machine Learning A-Z course with the received results being as questionable as they were back in the ML course.

I was incredibly satisfied with the Machine Learning A-Z course and I was met with a was very disappointing feeling when I realized that this course does not even remotely match up.

Watching part of the Machine Learning A-Z course has been very helpful.

After having completed the Machine Learning A-Z course I was eager to venture into Deep Learning.

A lot of the content was already covered in the Machine Learning A-Z course.

Loved the Deep Learning Course as well after Machine Learning A-Z Course.

boltzmann machines

on the second part - very good elaboration, but one recommendation - would be good if you could add a little bit to the Boltzmann machines and the Auto-encoders parts of the course.

Boltzmann Machines?

auto encoders

Though personally i struggled quite a bit on the boltzmann machines and auto encoders ... but the ANN, CNN and SOMs were absolutely amazing..As a next step, I feel i would need a more holistic and comprehensive course on recommender systems alone...

The last section can be changed to include Keras implementation of auto encoders, more use-cases of the discussed algorithms rather than repetitive content from other courses.

Overall: The course content was what I expected and I learned a lot about the different data regression techniques, machine learning Python libraries and the various deep learning theories, applications and implementations -- ANN, CNN, RNN, Boltzmann, SOM and Auto encoders.

I really like that the Boltzmann Machines and Auto Encoders are also covered here.

boltzmann machine and auto encoders (highly disappointing) It's an excellent course that introduces several interesting and useful technologies.

However, i didn't realize what is the advantage of auto encoders over ANN/RNN .

ANN and CNN has been explained superbly ... so is SOM ... but RNN and Auto Encoders were difficult to comprehend , especially the RNN , rest definitely worth it , too good to start off I enjoyed the course because it covers a lot of ground in good enough detail giving a good understanding of how and when to apply the techniques described.

I wish they had supplemented their code-videos (especially: Recurrent Neural Networks, Boltzman Machines & Auto Encoders) with some written material/flow-charts/algorithms...

Something that at least can be converted to features encoder, like convolutional neural networks (we can use CAE) or ordinary auto encoders.

The course was good for understanding neural networks (basic neural nets, convolutional, and recurrent) but it began to lose me when it went into Boltzmann machines and Auto Encoders.

additional reading material

great course, easy-to-understand explanation and the instructor also pointed out many helpful additional reading materials.

The additional reading material provided is in a large part consisting of academic papers, and those who do not already have a solid mathematical background might find it hard to navigate through it.

high level overview

Well it's really Hands-On course, despite I personally was expecting more deeper theoretical focus in this course it gives a very nice high level overview (referring to good theoretical materials).

I liked the fast pace of the course skimming through different topics giving high level overview of deep learning.

real world problems

I''m excited to learn how we can implement them to real world problems.

The code labs are also excellent and I've already been able to apply the knowledge to real world problems.

artificial intelligence

It taught me so much about Artificial Intelligence and Deeplearning.

And I am looking forward to start my next course, Artificial Intelligence A-Z: How to build an AI.

Careers

An overview of related careers and their average salaries in the US. Bars indicate income percentile.

Learning Services $59k

Computer Vision, Deep Learning Engineer $67k

Computer Vision & Deep Learning Engineer $67k

Deep Clean Sales Specialist $76k

Deep clean specialist $76k

Deep Learning Research Scientist $86k

Deep Learning Research Engineer $88k

Research Scientist - Deep Learning $91k

Senior Learning Specialist, Learning and Development $102k

Deep Learning R&D Engineer $127k

Learning Assitant $142k

Deep Submergence Systems Program Manager $157k

Write a review

Your opinion matters. Tell us what you think.

Rating	4.3★ based on 3,741 ratings
Length	22.5 total hours
Starts	On Demand (Start anytime)
Cost	$12
From	Udemy
Instructors	Kirill Eremenko, Hadelin de Ponteves, SuperDataScience Team, Ligency I Team, Ligency Team
Download Videos	Only via the Udemy mobile app
Language	English
Subjects	Data Science Business
Tags	Data Science Business Development Data & Analytics

Similar Courses

Sorted by relevance

Like this course?

Here's what to do next:

Save this course for later
Get more details from the course provider
Enroll in this course

Enroll Now

Deep Learning A-Z™

Hands-On Artificial Neural Networks

Get a Reminder

Get a Reminder

Similar Courses

What people are saying

Careers

Write a review

Please login to leave a review

Similar Courses

Like this course?

Special thanks to our sponsors