Cette formation vous apprendra à construire des modèles pour le langage naturel, l’audio et les autres données de séquence. Grâce à l’apprentissage profond, les algorithmes de séquence fonctionnent beaucoup mieux qu’il y a deux ans ; nous disposons donc de nombreuses applications très intéressantes en matière de reconnaissance vocale, de synthèse musicale, de chatbots, de traduction automatique, de compréhension naturelle du langage, etc.
Skills you'll gain
Details to know
Add to your LinkedIn profile
3 assignments
See how employees at top companies are mastering in-demand skills
Earn a career certificate
Add this credential to your LinkedIn profile, resume, or CV
Share it on social media and in your performance review
There are 3 modules in this course
Découvrez les réseaux neuronaux récurrents. Ce type de modèle s’est avéré extrêmement performant sur les données temporelles. Il comporte plusieurs variantes, y compris les LSTM, les GRU et les RNN bidirectionnels, que vous allez découvrir dans cette section.
What's included
12 videos2 readings1 assignment3 programming assignments3 ungraded labs
Le traitement du langage naturel avec l'apprentissage profond est une combinaison importante. En utilisant des représentations de vecteurs de mots et des couches de prolongements, vous pouvez former des réseaux neuronaux récurrents avec des performances exceptionnelles, dans une grande variété de secteurs. Des exemples d’applications sont l’analyse de sentiments, la reconnaissance d’entités nommées et la traduction automatique.
What's included
10 videos1 reading1 assignment2 programming assignments2 ungraded labs
Les modèles de séquence peuvent être améliorés à l’aide d’un mécanisme d’attention. Cet algorithme aidera votre modèle à comprendre où celui-ci doit focaliser son attention, compte tenu d’une séquence d’entrées. Cette semaine, vous apprendrez également à reconnaître la parole et à gérer les données audio.
What's included
11 videos3 readings1 assignment2 programming assignments2 ungraded labs
Offered by
Recommended if you're interested in Machine Learning
University of California, Irvine
Icahn School of Medicine at Mount Sinai
École Polytechnique Fédérale de Lausanne
University of Alberta
Why people choose Coursera for their career
New to Machine Learning? Start here.
Open new doors with Coursera Plus
Unlimited access to 7,000+ world-class courses, hands-on projects, and job-ready certificate programs - all included in your subscription
Advance your career with an online degree
Earn a degree from world-class universities - 100% online
Join over 3,400 global companies that choose Coursera for Business
Upskill your employees to excel in the digital economy
Frequently asked questions
Access to lectures and assignments depends on your type of enrollment. If you take a course in audit mode, you will be able to see most course materials for free. To access graded assignments and to earn a Certificate, you will need to purchase the Certificate experience, during or after your audit. If you don't see the audit option:
The course may not offer an audit option. You can try a Free Trial instead, or apply for Financial Aid.
The course may offer 'Full Course, No Certificate' instead. This option lets you see all course materials, submit required assessments, and get a final grade. This also means that you will not be able to purchase a Certificate experience.
When you purchase a Certificate you get access to all course materials, including graded assignments. Upon completing the course, your electronic Certificate will be added to your Accomplishments page - from there, you can print your Certificate or add it to your LinkedIn profile. If you only want to read and view the course content, you can audit the course for free.
You will be eligible for a full refund until two weeks after your payment date, or (for courses that have just launched) until two weeks after the first session of the course begins, whichever is later. You cannot receive a refund once you’ve earned a Course Certificate, even if you complete the course within the two-week refund period. See our full refund policy.