PyData Yerevan 2022

Cifar-10 Exploratory Data Analysis
08-12, 13:45–14:25 (Asia/Yerevan), 114W PAB

Image classification datasets are completed from the analysis point of view taking into account complicated structure of images. However the understanding of the dataset descriptors in the high level can add debugging facilities and in early stage predict the quality of the classification model. During this session we will visually analyze one of the challenging SOTA dataset like Cifar-10.

The datasets in AI used to contain 1000+ images. Images are matrices and the handling of available features, missing features that can lead to AI model overfitting or underfitting. Based on visualization will predict whether we can reduce the dataset and come-up to smaller set and predict its impact on final AI model.

Prior Knowledge Expected

Previous knowledge expected

CEO, co-founder at FiveBrane
3 years CTO at 50+, multi regional, ISO certified company
15+ years in IT
20+ publications in quantum physics
President Prize 2011 in Physics