Zurück zu Neuronale Netzwerke und Deep Learning

4.9

Sterne

71,162 Bewertungen

•

13,660 Bewertungen

If you want to break into cutting-edge AI, this course will help you do so. Deep learning engineers are highly sought after, and mastering deep learning will give you numerous new career opportunities. Deep learning is also a new "superpower" that will let you build AI systems that just weren't possible a few years ago.
In this course, you will learn the foundations of deep learning. When you finish this class, you will:
- Understand the major technology trends driving Deep Learning
- Be able to build, train and apply fully connected deep neural networks
- Know how to implement efficient (vectorized) neural networks
- Understand the key parameters in a neural network's architecture
This course also teaches you how Deep Learning actually works, rather than presenting only a cursory or surface-level description. So after completing it, you will be able to apply deep learning to a your own applications. If you are looking for a job in AI, after this course you will also be able to answer basic interview questions.
This is the first course of the Deep Learning Specialization....

Feb 12, 2018

I would love some pointers to additional references for each video. Also, the instructor keeps saying that the math behind backprop is hard. What about an optional video with that? Otherwise, awesome!

Jun 26, 2018

Really, really good course. Especially the tips of avoiding possible bugs due to shapes. Also impressed by the heroes' stories. Genuinely inspired and thoughtfully educated by Professor Ng. Thank you!

Filtern nach:

von sahil m

•Aug 20, 2018

Andrew sir introduces the idea of neural networks using a single neuron(logistic regression) and slowly adding complexity — more neurons and layers. By the end of the 4 weeks(course 1), we are introduced to all the core ideas required to build a dense neural network such as cost/loss functions, learning iteratively using gradient descent and vectorized parallel python(numpy) implementations.

Andrew patiently explains the requisite math and programming concepts in a carefully planned order and a well regulated pace suitable for learners who could be rusty in math/coding. I love this course.

von Ye W

•Oct 28, 2017

This course serves as a great intro. I saw many comments complaining that the course is a bit too easy. As a stats PhD student, I admit that the technical details in this initial course is trivial, but I feel that I learned a lot of useful things, e.g., vectorization, intuition, etc. In fact, the entire concept of deep neural net is very straightforward, i.e., nothing but a generalized linear model (GLM) from a statistical prospective. I feel what is important is the intuition behind it and how to implement it efficiently in practice. This course covers both aspects in great details, love it!

von Qiongxue S

•Dec 14, 2018

This course helps me to understand what is neural network and how would we use the NN and deep learning method to solve the practical problem. This is real science. For the content I have to say that this is the best AI course I have ever had. The related theory and mathematic equations are all clearly explained. Besides I learned a lot from every assignment. The point to build NN is make sure we understand the theory first then the programming part will not be hard. But before learning the course I think we need to have basic knowledge about python. Excellent course! Thank you so much.

von Chris R

•Sep 09, 2017

I have already completed Andrew Ng's Stanfor Machine Learning course on Coursera, but the neural network coverage was limited. This course helped me understand the underlying principles of deep learning more completely and I'll be taking all five to earn the specialization. The pace of this course seemed perfect for me having some knowledge of Python, linear algebra, and calculus. This course also helped to refresh older memories and learn new things about Python libraries like numpy. This is an excellent course and has left me very excited about possible applications for deep learning.

von vuhaluu

•Aug 20, 2017

I took the ML matlab version that Prof Ng created, but could not make it because I could not understand the homework problems and the content of the course. Thus, I got out after the fifth week because I could not understand how to do the assignment. However, luckily, right after I got out, he opened this course. It was a relief that I was able to understand everything I did not understand from the previous one, and I was able to do the homework. Therefore, I would suggest this course to everyone who wants to learn AI. Thank you Prof Ng and your dedicated team for this tremendous effort!

von Hugo M S P

•Dec 06, 2017

I loved this course and I got much more inspired to pursuit my search in this area hoping that one day I can join this amazing community and get a job in this area!

Thank you very much for your great work: loved the good sequencing of the videos, with very simple and bright intuitions about the more complex math topics, and also enjoyed a lot the Interviews with the gurus/legends of AI and ML!

Congratulations to all that participated and made such a great effort to put up this course available in such a professional format and by such a filantropic price!

Keep on with this outstanding job!

von George Z

•May 20, 2019

The Neural Networks and Deep Learning class from Andrew Ng, deeplearning.ai and Coursera is very well structured and taught. I learned a lot and I am glad I was able to use calculus and Python to better understand what is going on underneath the hood with forward propagation, cost, parameters, backward propagation, predictions and more. Andrew and his team are exceptional instructors. The Deep Learning hero sessions are very motivational and inspiring. I also enjoy Andrew's sessions from Stanford's CS230 online. Looking forward to my next adventure in this Deep Learning Specialization.

von HEF

•Mar 24, 2019

Before taking this course I have learned Machine Learning, which is another famous course in Coursera, also taught by Professor Ng. My feeling is that this course is not as intensive as that one, but still I learned so many new stuffs which are extremely useful in my own deep learning projects. Before taking this course, I had zero coding experience in Python and so was really nervous about the programming exercises. However, the exercises are very well organized that I think every one can handle easily. So what I want to say is, don't say you can't do it if you never give it a try.

von Ronak V

•Oct 15, 2017

Not sure how other people would fare, but I felt like in order to have a deep understanding of what was actually going on, I needed to go study the calculus and linear algebra behind the material (which I had done previously). I know that probably turns a lot of people off and is why it's somewhat glossed over, but thought I'd just put it out there.

I will say that this course was super helpful with seeing how a theoretical understanding of DL translates into code. The coding exercises were 100/100. So thank you for that! :). Looking forward to the next courses in the specialization!

von barryhf

•Mar 28, 2019

It's an honor to be taught by Professor Ng. He's an excellent instructor, and he has very effectively brought this complex material to those of us who are practitioners rather than applied mathematicians.

Perhaps if, like me, you are familiar with the mathematics used in this work, you might find the pace a bit slow. The repetition, and the guided programming exercises, do serve a valuable purpose. By the end, by the final exercise, there is crisp clarity on what all of the components of the neural network are, and how they are utilized.

Thank you, professor, for an excellent course.

von Mohammad S Q

•Feb 19, 2019

First of all the course is designed and taught by AI pioneer Andrew Ng, the fact itself creates no room for any reason for not opting for this course if somebody wants to learn about DL.

Secondly, the approach is ground up, you get a confidence that without knowing or learning complex numerical foundations, you can get intuition of how deep learning works and can very well start applying this into your projects. When you see working model of a deep neural network built from fundamental codes, you feel like doing something and it makes you try harder and wider problems on your own.

von Naima

•Sep 27, 2017

The course is very helpful. Andrew Ng has explained all the basics of neural networks. Both theory and programming lessons are very neatly arranged. It helps freshers to learn a lot. Since in programming assignment, the theory and notations needed for that are also explained I could connect everything fast. And I didn't had to code everything in python. It helps people who are not that much expert in python and its an inspiration to learn more in python and other technologies. I express my gratitude towards Coursera and Mr.Andrew Ng for helping for this course. Thanks, Naima Vahab

von Christen

•Sep 09, 2017

I had almost zero knowledge about Python language and even less about all the complexity of the internal structure of neural networks (NN). I can imagine how difficult is teaching this sort of witchery to common mortals but Andrew Ng. did a great job on that simplifying and remarking just the practical and important points you require to build a simple NN. It's a clever way to start in the world of deep learning despite of the high price of this course, otherwise it could take ages learning by yourself. I wonder if I will become a kind of wizard when I finish all the 5 courses...

von Sabarish V

•Dec 03, 2018

The course takes a very direct approach to building your first neural network. It has very little maths, and the coding is extremely simplified in the assignments. For someone with a little bit of background, it wouldn't take more than a couple hours to be done with the course and running your first multi-layer model. If you have prior knowledge of NNs, machine learning, or calculus and vectorization, the course could feel a bit tedious. In this case, I'd recommend running the videos at 1.5x or 2x speed .

My only gripe is the quality of the audio. It could have been much better.

von Eche I

•Oct 12, 2018

I was initially running from the maths that underpins deep learning but this course made it some much easy to understand and gain intuition on how to operate deep learning. I thoroughly enjoyed Andrew's style of delivery and with his constant reassurance and I quote, "don't worry about it …", that holds very true and gradually makes you fall and gets the underlying linear algebra, calculus and derivatives that form the theoretical backbone of deep learning. The course really left me on the high and with a strong grounding to begin to press further in this deep learning journey.

von Assaf B

•Aug 22, 2018

If you had Prof Ng's "Machine learning" in the past, you expect perfection, so you may say that this course had imperfections such as Jupyter work instead of offline work, which confines your creativity when working on an exercise, and the course bit short, even for a chapter in a specialization.

However, when comparing to other courses, to nearly any other MOOC except "Machine learning" and perhaps "Complex Analysis", this course is still a DEFINITE five stars course. In content, in knowledge bang for your time invested, in usefulness, in teaching ability, and the list goes on.

von Karim W E A

•Aug 15, 2017

A lot of repeated material from Stanford's Introduction to Machine Learning, especially week 4. But of course, implementing all the assignments in Python, which is probably the most widely used language for ML and one of the most efficient ones as well; That was a big advantage over the material covered in Introduction to Machine Learning. Also, the material was explained in great detail and was tremendously organized. Would highly recommend the course to anyone who's looking into expanding their knowledge in Deep Learning. I can't wait to start Course 2 in the specialization!

von Ricardo S

•Nov 24, 2017

I found this course to be a good introduction to neural networks and deep learning geared toward the uninitiated. For anyone with some experience however, the course can be rather easy, though it can serve as a review and it is fast enough to go through. I find it to be always good to start from basics, especially in the complex and always evolving field of machine learning, and this is an adequate starting point. I suggest that anyone taking this course with serious aims should seek to understand the mathematics introduced in it, though it is often mentioned as "not needed".

von Mark M

•Jun 20, 2019

The programming assignments in this course provide practical experience in building a deep learning neural network. The lectures are thorough and easy to understand, and they connect clearly to the quizzes and assignments. I'm grateful that Professor Ng and staff put this excellent resource together and make it accessible to all. I currently work in Cambodia, where I hope to introduce courses such as this to young people who have no educational opportunities. I highly recommend this course to all who wish to be aware of the incremental significance of AI in our time. Thanks!

von Aayush K S

•Apr 06, 2019

Really great course material. With minimal mathematics behind this, this course provided a great start to deep dive into deep learning. The video length and the quizzes and exercises were great. Also, since jupyter notebook was hosted by coursera itself, I didn't had to invest setting up infrastructure or downloading packages in my local system which was unlike AndrewNg's MachineLearning course which used Octave. This experience made completing the exercises more efficiently. helping me to utilize most of my time in solving it. Looking forward to complete the next courses.

von Matteo C

•Mar 08, 2018

A great course.

The topic is very compelling on its own, but the magic is all in the instructor. Andrew Ng is passionate and explains complex concepts by slowly building up to them. It was very important for me that he introduced the math and notation required, without assuming a lot of prior knowledge.

The programming assignments are worked on and submitted with Jupiter notebooks, which is great.

To make the most of this course, I would recommend doing the "Machine Learning" course from Andrew Ng, as it has a lot of relevant content and a good refresher on linear algebra.

von Casey K

•Mar 08, 2018

Definitely recommended. I've taken various other deep-learning lessons and tutorials, but none of them gave me as much insight and practice as this course. I get the feeling that a lot of work went into the design of the course and even the homework problems.

A practical note for people considering the class: it'd be a good idea to review how matrix multiplication works before diving in, because that comes up again and again. There's a review in the course itself, but it doesn't come until week 4, and I found it necessary to analyze matrix dimensions as early as week 2.

von Abdur R K

•Dec 24, 2017

Amazing course! I didn't even know python when I begun properly (only C++,C and C# and octave/MATLAB) but all the required functions/commands were introduced in a way that I faced no issues whatsoever. Of course I did need to google a lot of syntax differences (like for loops and stuff), but the experience was very fluid and everything connects extremely well to Andrew's famous Stanford ML course. If you're somebody who has only taken that course and are wondering if you can take the Deep learning specialization without having to study python first, I would say GO FOR IT!

von Самигуллин А

•Dec 23, 2017

Very good course that can build understanding of neural networks and machine learning key concepts in a straight way. It is also interesting for some people, who thinks that he is advanced in machine learning, like me, but have only conceptual understanding of neural nets and no coding practice (just some experience with visual matlab plugin for NN).

Thanks for professor Ng and his deeplearning.ai team for preparing this course and for Coursera team for hosting it and making available.

P.S. It is so cool course that I'm helping with translation of this course to Russian.

von Francois R

•Jun 30, 2018

The Super Excellent: How the course is built, with a lot of small block well placed on top of each others. The honest rendering (cutting over the hype) by Andrew Ng of DL and ML in general.The Excellent: The new notation and organization of the matrices (compared to Andrew Ng's previous Machine Learning course). The new explanation of backward propagation.The Good: The use of caches between Forward Prop. and Backward Prop., but also between the different functions. Note: The latter would benefit cleaner names and the usage of assert() on entry of the functions.Thanks,

- KI für alle
- Vorstellung von TensorFlow
- Neuronale Netzwerke und Deep Learning
- Algorithmen, Teil 1
- Algorithmen, Teil 2
- Maschinelles Lernen
- Maschinelles Lernen mit Python
- Maschinelles Lernen mittels Sas Viya
- R-Programmierung
- Einführung in die Programmierung mit Matlab
- Datenanalyse mit Python
- AWS-Grundlagen: Mit der Cloud vertraut werden
- Grundlagen der Google Cloud-Plattform
- Engineering für Site-Funktionssicherheit
- Englisch im Berufsleben
- Die Wissenschaft des Wohlbefindens
- Lernen lernen
- Finanzmärkte
- Hypothesenüberprüfung im öffentlichen Gesundheitswesen
- Grundlagen für Führungsstärke im Alltag

- Deep Learning
- Python für alle
- Data Science
- Angewandte Datenwissenschaft mit Python
- Geschäftsgründungen
- Architektur mit der Google Cloud-Plattform
- Datenengineering in der Google Cloud-Plattform
- Von Excel bis MySQL
- Erweiterte maschinelles Lernen
- Mathematik für maschinelles Lernen
- Selbstfahrende Autos
- Blockchain-Revolution für das Unternehmen
- Unternehmensanalytik
- Excel-Kenntnisse für Beruf
- Digitales Marketing
- Statistische Analyse mit R im öffentlichen Gesundheitswesen
- Grundlagen der Immunologie
- Anatomie
- Innovationsmanagement und Design Thinking
- Grundlagen positiver Psychologie