サクサク読めて、アプリ限定の機能も多数!
トップへ戻る
Pixel 9
research.facebook.com
We introduce LLaMA, a collection of foundation language models ranging from 7B to 65B parameters. We train our models on trillions of tokens, and show that it is possible to train state-of-the-art models using publicly available datasets exclusively, without resorting to proprietary and inaccessible datasets. In particular, LLaMA-13B outperforms GPT-3 (175B) on most benchmarks, and LLaMA-65B is co
Presto: SQL on EverythingIEEE International Conference on Data Engineering (ICDE) Presto is an open source distributed query engine that supports much of the SQL analytics workload at Facebook. Presto is designed to be adaptive, flexible, and extensible. It supports a wide variety of use cases with diverse characteristics. These range from user-facing reporting applications with sub-second latency
Machine Learning at Facebook: Understanding Inference at the EdgeIEEE International Symposium on High-Performance Computer Architecture (HPCA) At Facebook, machine learning provides a wide range of capabilities that drive many aspects of user experience including ranking posts, content understanding, object detection and tracking for augmented and virtual reality, speech and text translations. Whi
Facebookで投稿や写真などをチェックできます。
Today, Facebook AI Research (FAIR) open sourced DensePose, our real-time approach for mapping all human pixels of 2D RGB images to a 3D surface-based model of the body. Recent research in human understanding aims primarily at localizing a sparse set of joints, like the wrists, or elbows of humans. This may suffice for applications like gesture or action recognition, but it delivers a reduced image
State-of-the-art visual perception models for a wide range of tasks rely on supervised pretraining. ImageNet classification is the defacto pretraining task for these models. Yet, ImageNet is now nearly ten years old and is by modern standards small. Even so, relatively little is known about the behavior of pretraining with datasets that are multiple orders of magnitude larger. The reasons are obvi
Facebookにログインして、友達や家族と写真や近況をシェアしましょう。
ResourcesResources and tools for advancing AI, together Cutting-edge open source frameworks, tools, libraries, datasets and models for research exploration to large-scale production deployment. Frameworks and tools Sharing our ML frameworks and tools with the community to collaborate and accelerate the advancement of AI
Applied Machine Learning at Facebook: A Datacenter Infrastructure PerspectiveInternational Symposium on High-Performance Computer Architecture (HPCA) Machine learning sits at the core of many essential products and services at Facebook. This paper describes the hardware and software infrastructure that supports machine learning at global scale. Facebook’s machine learning workloads are extremely d
SVE: Distributed Video Processing at Facebook ScaleSymposium on Operating Systems Principles (SOSP) Videos are an increasingly utilized part of the experience of the billions of people that use Facebook. These videos must be uploaded and processed before they can be shared and downloaded. Uploading and processing videos at our scale, and across our many applications, brings three key requirements:
Accurate, Large Minibatch SGD: Training ImageNet in 1 HourData @ Scale Deep learning thrives with large neural networks and large datasets. However, larger networks and larger datasets result in longer training times that impede research and development progress. Distributed synchronous SGD offers a potential solution to this problem by dividing SGD minibatches over a pool of parallel workers. Yet
A 61-million-person experiment in social influence and political mobilizationNature Human behaviour is thought to spread through face-to-face social networks, but it is difficult to identify social influence effects in observational studies, and it is unknown whether online social networks operate in the same way. Here we report results from a randomized controlled trial of political mobilization
Realtime data processing powers many use cases at Facebook, including realtime reporting of the aggregated, anonymized voice of Facebook users, analytics for mobile applications, and insights for Facebook page administrators. Many companies have developed their own systems; we have a realtime data processing ecosystem at Facebook that handles hundreds of Gigabytes per second across hundreds of dat
Practical Lessons from Predicting Clicks on Ads at FacebookInternational Workshop on Data Mining for Online Advertising (ADKDD) Online advertising allows advertisers to only bid and pay for measurable user responses, such as clicks on ads. As a consequence, click prediction systems are central to most online advertising systems. With over 750 million daily active users and over 1 million active ad
Several weeks ago, Sarah Larson from The New Yorker published a fun article about e-laughter (all the hahas and lols we use to communicate with our friends online) and their social subtleties. Like any “dialect,” e-laughing is evolving. Curious as to whether her usage followed up-to-date social norms, she consulted her savvy friends for answers. Anecdotally, she found that laughter tended to vary
DeepFace: Closing the Gap to Human-Level Performance in Face VerificationConference on Computer Vision and Pattern Recognition (CVPR) In modern face recognition, the conventional pipeline consists of four stages: detect => align => represent => classify. We revisit both the alignment step and the representation step by employing explicit 3D face modeling in order to apply a piecewise affine transf
次のページ
このページを最初にブックマークしてみませんか?
『このページを見るには、ログインまたは登録してください』の新着エントリーを見る
j次のブックマーク
k前のブックマーク
lあとで読む
eコメント一覧を開く
oページを開く