research
∙
11/08/2022
Linear Self-Attention Approximation via Trainable Feedforward Kernel
In pursuit of faster computation, Efficient Transformers demonstrate an ...
share
research
∙
10/20/2022
Graph Neural Networks with Trainable Adjacency Matrices for Fault Diagnosis on Multivariate Sensor Data
Timely detected anomalies in the chemical technological processes, as we...
research
∙
11/23/2021
SimpleTron: Eliminating Softmax from Attention Computation
In this paper, we propose that the dot product pairwise matching attenti...
research
∙
09/20/2021