Realtime tSNE Visualizations with TensorFlow.js
Posted by Nicola Pezzotti, Software Engineering Intern, Google Zürich In recent years, the t-distributed Stochastic Neighbor Embedding (tSNE) algorithm has become one of the most used and insightful techniques for exploratory data analysis of high-dimensional data. Used to interpret deep neural network outputs in tools such as the TensorFlow Embedding Projector and TensorBoard, a powerful feature
1
リリース、障害情報などのサービスのお知らせ
最新の人気エントリーの配信
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
Multimodal medical AI
MLGO: A Machine Learning Framework for Compiler Optimization
Auto-generated Summaries in Google Docs
A Fast WordPiece Tokenization System
Background Features in Google Meet, Powered by Web ML
Introducing Translatotron: An End-to-End Speech-to-Speech Translation Model
Google AI Blog: TF-Ranking: A Scalable TensorFlow Library for Learning-to-Rank
Building Google Dataset Search and Fostering an Open Data Ecosystem
Announcing Cirq: An Open Source Framework for NISQ Algorithms
Introducing Google AI
Announcing the Google Cloud Platform Research Credits Program
SLING: A Natural Language Frame Semantic Parser
Announcing AudioSet: A Dataset for Audio Event Research
Bringing Precision to the AI Safety Discussion
Motion Stills – Create beautiful GIFs from Live Photos