Explore >> Select a destination

You are here

 jaketae.github.io
Linear Attention Computation in Nyströmformer - Jake Tae
| | teddykoker.com
Performers: The Kernel Trick, Random Fourier Features, and Attention | Teddy Koker
4.1 parsecs away

Travel
| | Google AI recently released a paper, Rethinking Attention with Performers (Choromanski et al., 2020), which introduces Performer, a Transformer architecture which estimates the full-rank-attention mechanism using orthogonal random features to approximate the softmax kernel with linear space and time complexity. In this post we will investigate how this works, and how it is useful for the machine learning community.
| | randorithms.com
How to Find the Taylor Series of an Inverse Function - Randorithms
5.0 parsecs away

Travel
| | The Taylor series is a widely-used method to approximate a function, with many applications. Given a function \(y = f(x)\), we can express \(f(x)\) in terms ...
| | sigmoidprime.com
Transformer-XL: A Memory-Augmented Transformer
5.0 parsecs away

Travel
| | An exploration of Transformer-XL, a modified Transformer optimized for longer context length.
| | wtfleming.github.io
Cats vs Dogs - Part 3 - 99.1% Accuracy - Binary Image Classification with PyTorch and an Ensemble of ResNet Models
16.6 parsecs away

Travel
| [AI summary] This post discusses achieving 99.1% accuracy in binary image classification of cats and dogs using an ensemble of ResNet models with PyTorch.