article thumbnail

For your eyes only: improving Netflix video quality with neural networks

The Netflix TechBlog

Recently, we added another powerful tool to our arsenal: neural networks for video downscaling. In this tech blog, we describe how we improved Netflix video quality with neural networks, the challenges we faced and what lies ahead. How can neural networks fit into Netflix video encoding?

Network 292
article thumbnail

Building In-Video Search

The Netflix TechBlog

We have built an internal system that allows someone to perform in-video search across the entire Netflix video catalog, and we’d like to share our experience in building this system. The recent success of large-scale models that jointly train image and text embeddings has enabled new use cases around multimodal retrieval.

Media 225
Insiders

Sign Up for our Newsletter

This site is protected by reCAPTCHA and the Google Privacy Policy and Terms of Service apply.

Trending Sources

article thumbnail

A Comprehensive Guide to Hyperparameter Tuning: Exploring Advanced Methods

DZone

Hyperparameter tuning is an essential practice in optimizing the performance of machine learning models. This article provides an in-depth exploration of advanced hyperparameter tuning methods, including Population-Based Training (PBT), BOHB, ASHA, TPE, Optuna, DEHB, Meta-Gradient Descent, BOSS, and SNIPER.

Tuning 141
article thumbnail

Detecting Speech and Music in Audio Content

The Netflix TechBlog

Practical use cases for speech & music activity Audio dataset preparation Speech & music activity is an important preprocessing step to prepare corpora for training. Content, genre and languages Instead of augmenting or synthesizing training data, we sample the large scale data available in the Netflix catalog with noisy labels.

article thumbnail

The Performance Inequality Gap, 2024

Alex Russell

It's time once again to update our priors regarding the global device and network situation. The usual caveats also apply: Performance is a deep and nuanced domain, and much can go wrong beyond content size and composition. How sites manage resources after-load can have a big impact on perceived performance.

article thumbnail

Snuba: automating weak supervision to label training data

The Morning Paper

Snuba: automating weak supervision to label training data Varma & Ré, VLDB 2019. It’s tackling the same fundamental problem: how to gather enough labeled data to train a model, and how to effectively use it in a weak supervision setting (supervised learning with noisy labels). F1 points in terms of end model performance.

article thumbnail

AWS and Dynatrace automation hit the jackpot at Perform Las Vegas

Dynatrace

Well, that’s exactly what the Dynatrace University team did to support Dynatrace’s hands-on training (HoT) days at Dynatrace’s annual user conference Perform in Las Vegas. The Dynatrace dashboard below that shows the thousands of EC2 instances coming up and then being removed at the close of the training. Quite impressive!

AWS 169