Picture for Alexander Kovalenko

Alexander Kovalenko

Linear Self-Attention Approximation via Trainable Feedforward Kernel

Add code
Nov 08, 2022
Viaarxiv icon

Graph Neural Networks with Trainable Adjacency Matrices for Fault Diagnosis on Multivariate Sensor Data

Add code
Oct 20, 2022
Figure 1 for Graph Neural Networks with Trainable Adjacency Matrices for Fault Diagnosis on Multivariate Sensor Data
Figure 2 for Graph Neural Networks with Trainable Adjacency Matrices for Fault Diagnosis on Multivariate Sensor Data
Figure 3 for Graph Neural Networks with Trainable Adjacency Matrices for Fault Diagnosis on Multivariate Sensor Data
Figure 4 for Graph Neural Networks with Trainable Adjacency Matrices for Fault Diagnosis on Multivariate Sensor Data
Viaarxiv icon

SimpleTron: Eliminating Softmax from Attention Computation

Add code
Dec 02, 2021
Figure 1 for SimpleTron: Eliminating Softmax from Attention Computation
Figure 2 for SimpleTron: Eliminating Softmax from Attention Computation
Figure 3 for SimpleTron: Eliminating Softmax from Attention Computation
Figure 4 for SimpleTron: Eliminating Softmax from Attention Computation
Viaarxiv icon

Dynamic Neural Diversification: Path to Computationally Sustainable Neural Networks

Add code
Sep 20, 2021
Figure 1 for Dynamic Neural Diversification: Path to Computationally Sustainable Neural Networks
Figure 2 for Dynamic Neural Diversification: Path to Computationally Sustainable Neural Networks
Figure 3 for Dynamic Neural Diversification: Path to Computationally Sustainable Neural Networks
Figure 4 for Dynamic Neural Diversification: Path to Computationally Sustainable Neural Networks
Viaarxiv icon