RT @ghandeharioun: 🧵Responses to adversarial queries can still remain latent in a safety-tuned model. Why are they revealed sometimes, but….

RT @maxbittker: 🎭 ✨ is a new website for writing and playing with indie face filters! . Try playing with the preset….

RT @TensorFlow: ML for the Web and Beyond 🚀. TensorFlow.js is the key to training and deploying ML models in browsers or anywhere #JavaScri….

Hooray!.

What does it mean?.

RT @TensorFlow: 📢 Blazeface is now available in browsers with TensorFlow.js! . The model detects faces and facial features in real-time 👨👩⏰….

RT @_coenen: Understanding UMAP - a high-level introduction to how the algorithm works, how to use it effectively, and how it compares with….

RT @emilyrreif: How are semantics and word senses represented in contextual word embeddings? Visualizations, blogpost, and paper by @GreenB….

RT @nsthorat: Go outside.

RT @TensorFlow: We just released PoseNet 2.0 with TensorFlow.js, including a much more accurate ResNet-based model!. Try the live demo by @….

RT @nsthorat: Check out UMAP.js, a dimensionality reduction algorithm adapted for JavaScript by my awesome coworker @_coenen .

The Universal Sentence Encoder is now in TensorFlow.js! . USE gives you embeddings for text. It's a great starting point for doing sentiment analysis, topic classification, measuring textual similarity, etc.

RT @williamngan: Wow, tensorflow.js posenet is so much faster than when I first tried it 6 months ago. Quick test. #tfjs #ptsjs https://t.c….

RT @ManningMEAP: New MEAP! Deep Learning with JavaScript by Shanqing Cai, Stanley Bileschi, Eric D. Nielsen with @fchollet .

mean, median, and mode. how did mode get in there.

Crabs are the pomegranates of meat.

RT @mbostock: The de Jong attractor in WebGL.