Search Results for author:
Found 3 papers, 3 papers with code
Going Beyond Linear Transformers with Recurrent Fast Weight Programmers
Transformers with linearised attention ("linear Transformers") have demonstrated the practical scalability and effectiveness of outer product-based Fast Weight Programmers (FWPs) from the '90s.
Are Neural Nets Modular? Inspecting Functional Modularity Through Differentiable Weight Masks
Neural networks (NNs) whose subnetworks implement reusable functions are expected to offer numerous advantages, including compositionality through efficient recombination of functional building blocks, interpretability, preventing catastrophic interference, etc.
Improving Differentiable Neural Computers Through Memory Masking, De-allocation, and Link Distribution Sharpness Control
The Differentiable Neural Computer (DNC) can learn algorithmic and question answering tasks.
Cannot find the paper you are looking for? You can
Submit a new open access paper.