Deriving Neural Architectures from Sequence and Graph Kernels
-
Updated
Nov 22, 2017 - Python
Deriving Neural Architectures from Sequence and Graph Kernels
[Neurips 2022] "Deep Architecture Connectivity Matters for Its Convergence: A Fine-Grained Analysis" by Wuyang Chen*, Wei Huang*, Xinyu Gong, Boris Hanin, Zhangyang Wang
A complete convolutional neural network implemented from scratch
A scalable, reasoning-centric neural architecture with Mixture-of-Experts, dynamic compute allocation, and long-context modeling up to 256K tokens
A training method for neural networks that dynamically adjust the size of layers.
Final Project about optimizing NN with Bayesian Optimization for Bayesian Methods in ML course in Washington University
Add a description, image, and links to the neural-architectures topic page so that developers can more easily learn about it.
To associate your repository with the neural-architectures topic, visit your repo's landing page and select "manage topics."