/explore

Click through on any links that interest you or select the planets on the right to continue exploring the Outer Web.
You are here

 jalammar.github.io
The Illustrated Transformer - Jay Alammar - Visualizing machine learning one concept at a time.
| | www.telesens.co
Understanding incremental decoding in fairseq | Telesens
2.9 parsecs away

Travel
| | [LatexPage] Recently, I've been learning about sequence-to-sequence translation systems and going through Pytorch's fairseq code. I've been focusing on the convolutional seq-to-seq method by Gehring et al. The basic idea behind seq-to-seq models is easy to understand, but there are a number of issues in the implementation that I found tricky to understand. In this post,
| | nlp.seas.harvard.edu
The Annotated Transformer
2.6 parsecs away

Travel
| | The Annotated Transformer
| | sigmoidprime.com
Transformer-XL: A Memory-Augmented Transformer
3.3 parsecs away

Travel
| | An exploration of Transformer-XL, a modified Transformer optimized for longer context length.
| | kevinlynagh.com
Towards the cutest neural network
14.8 parsecs away

Travel
| [AI summary] The author discusses their experience developing a simple neural network for sensor data processing on a microcontroller, highlighting challenges with quantization and inference optimization.