Ce que vous devez savoir avant
Vous commencez
Débute 4 June 2026 03:58
Se termine 4 June 2026
Machine Learning: Clustering & Retrieval
University of Washington
9 Cours
L'Université de Washington est une université publique de premier rang située à Seattle, offrant une éducation de classe mondiale aux étudiants de tous horizons. Son corps professoral diversifié, ses vastes opportunités de recherche et son programme d'études innovant créent une expérience d'apprentissage inégalée.
Non spécifié
Amélioration optionnelle disponible
Tous niveaux
Progressez à votre rythme
Free
Amélioration optionnelle disponible
Aperçu
Delve into the fascinating world of machine learning with the "Machine Learning:
Clustering & Retrieval" course, offered by the esteemed University of Washington through Coursera. This course stands as a beacon for those intrigued by artificial intelligence, Python programming, and the intricacies of both supervised and unsupervised learning.
Get ready to explore the realm of similarity-based algorithms for document retrieval, a crucial skill in today's data-driven landscape.
The course embarks on a journey through critical case studies, such as finding similar documents among millions. It challenges participants to define the right notion of similarity and introduces efficient strategies to retrieve documents without the need to sift through vast datasets.
Students will learn about structured document representations, clustering, and mixed membership models like latent Dirichlet allocation (LDA). Furthermore, the course dives deep into the implementation of expectation maximization (EM) to learn document clusterings and discusses scaling methods using MapReduce.
Upon completion, participants will be equipped to:
- Create a document retrieval system utilizing k-nearest neighbors.
- Understand and apply various text data similarity metrics.
- Optimize k-nearest neighbor search using KD-trees and approximate nearest neighbors with locality sensitive hashing.
- Discern the differences between supervised and unsupervised learning tasks.
- Cluster documents by topicality using k-means and parallelize k-means with MapReduce.
- Explore probabilistic clustering with mixture models and fit a Gaussian mixture model via expectation maximization (EM).
- Engage with mixed membership modeling employing latent Dirichlet allocation (LDA).
- Utilize Gibbs sampler for inferences and compare initialization techniques for non-convex objectives.
- Gain practical experience implementing these methodologies in Python.
This course targets not only the theoretical underpinnings of machine learning but also places a strong emphasis on practical application, making it an ideal learning path for individuals aiming to thrive in the fields of artificial intelligence, machine learning, and beyond.
Enroll today to start your journey towards mastering clustering and retrieval in machine learning.
Categories:
Artificial Intelligence Courses, Python Courses, Machine Learning Courses, Supervised Learning Courses.
