Dataset Groups Activity Stream MNIST and CIFAR-10 datasets The MNIST and CIFAR-10 datasets are used to test the theory suggesting the existence of many saddle points in high-dimensional functions. BibTex: @dataset{Daniel_Scheliga_and_Patrick_M¨ader_and_Marco_Seeland_2024, abstract = {The MNIST and CIFAR-10 datasets are used to test the theory suggesting the existence of many saddle points in high-dimensional functions.}, author = {Daniel Scheliga and Patrick M¨ader and Marco Seeland}, doi = {10.57702/wah3vt5y}, institution = {No Organization}, keyword = {'Adversarial Examples', 'CIFAR-10', 'Deep Learning', 'Federated Learning', 'Handwritten Digits', 'Handwritten digits', 'High-dimensional functions', 'Image Classification', 'Images', 'MNIST', 'Neural Networks', 'Saddle points', 'handwritten digits', 'image classification', 'images'}, month = {dec}, publisher = {TIB}, title = {MNIST and CIFAR-10 datasets}, url = {https://service.tib.eu/ldmservice/dataset/mnist-and-cifar-10-datasets}, year = {2024} }
