Explore >> Select a destination
|
You are here 
|
polukhin.tech | ||
| | | | |
d2l.ai
|
|
| | | | | [AI summary] This chapter provides an in-depth exploration of recommender systems, covering fundamental concepts and advanced techniques. It begins with an overview of collaborative filtering and the distinction between explicit and implicit feedback. The chapter then delves into various recommendation tasks and their evaluation methods. It introduces the MovieLens dataset as a practical example for building recommendation models. Subsequent sections discuss matrix factorization, AutoRec using autoencoders, personalized ranking with Bayesian personalized ranking and hinge loss, neural collaborative filtering, sequence-aware recommenders, feature-rich models, and deep factorization machines like DeepFM. The chapter concludes with implementation details and ev... | |
| | | | |
blog.ephorie.de
|
|
| | | | | ||
| | | | |
fodsi.us
|
|
| | | | | [AI summary] The ML4A Virtual Workshop explores how machine learning enhances classical algorithms through data-driven approaches, featuring talks on deep generative models, model-based deep learning, and learning-augmented algorithms. | |
| | | | |
iclr-blogposts.github.io
|
|
| | | Diffusion Models, a new generative model family, have taken the world by storm after the seminal paper by Ho et al. [2020]. While diffusion models are often described as a probabilistic Markov Chains, their underlying principle is based on the decade-old theory of Stochastic Differential Equations (SDE), as found out later by Song et al. [2021]. In this article, we will go back and revisit the 'fundamental ingredients' behind the SDE formulation and show how the idea can be 'shaped' to get to the modern form of Score-based Diffusion Models. We'll start from the very definition of the 'score', how it was used in the context of generative modeling, how we achieve the necessary theoretical guarantees and how the critical design choices were made to finally arri... | ||
