Batch normalization is sufficient for universal function approximation in CNNs

Authors: Rebekka Burkholz

ICLR 2024 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental To validate our theory, we explicitly match target networks that outperform experimentally obtained networks with trained BN parameters by utilizing a sufficient number of random features. ... 3 EXPERIMENTS
Researcher Affiliation Academia Rebekka Burkholz CISPA Helmholtz Center for Information Security 66123 Saarbrücken, Germany burkholz@cispa.de
Pseudocode No The paper discusses reconstruction algorithms but does not provide any structured pseudocode or algorithm blocks.
Open Source Code No The paper does not provide explicit statements or links to open-source code for the described methodology.
Open Datasets Yes We consider two standard image classifcation benchmark datasets, CIFAR10 and CIFAR100 (Krizhevsky, 2009)
Dataset Splits No The paper mentions using CIFAR10 and CIFAR100, which have standard splits, but does not explicitly state the training/validation/test dataset splits (e.g., percentages or sample counts) within the text.
Hardware Specification Yes All experiments were conducted on a machine with Intel(R) Core(TM) i9-10850K CPU @ 3.60GHz processor and GPU NVIDIA Ge Force RTX 3080 Ti
Software Dependencies No The paper mentions 'pytorchs torch.linalg.solve function' and 'Pytorchs torch.optim.LBFGS', indicating the use of PyTorch, but it does not specify version numbers for PyTorch or any other software dependencies.
Experiment Setup Yes We use a standard training procedure: SGD with 5 warmup epochs and linear learning rate increase, followed by 200 epochs of cosine annealing with initial learning rate 0.1.