Search Results for author:
Found 4 papers, 3 papers with code
Breaking the Architecture Barrier: A Method for Efficient Knowledge Transfer Across Networks
We present a method for transferring parameters between neural networks with different architectures.
Transfer Learning Between Different Architectures Via Weights Injection
This work presents a naive algorithm for parameter transfer between different architectures with a computationally cheap injection technique (which does not require data).
batchboost: regularization for stabilizing training with resistance to underfitting & overfitting
Pairing stage calculates the error per sample, sorts the samples and pairs with strategy: hardest with easiest one, than mixing stage merges two samples using mixup, $x_1 + (1-\lambda)x_2$.
Ranked #72 on
Image Classification
on CIFAR-10
Chessboard and chess piece recognition with the support of neural networks
However, its solution is crucial for many experienced players who wish to compete against AI bots, but also prefer to make decisions based on the analysis of a physical chessboard.
