Introducing Machine Learning Concepts by Training a Neural Network to Recognize Hand Gestures

Abstract

We present an interactive guided activity to introduce supervised learning by training a deep neural network (treated as a black box) to recognize "rock paper scissors" hand gestures from unconstrained images. The audience is actively involved in acquiring a varied and representative dataset, on which the rest of the activity is based. Covered concepts include the training/evaluation split, classifier evaluation, baseline accuracy, overfitting, generalization, data augmentation.

Cite

Text

Giusti et al. "Introducing Machine Learning Concepts by Training a Neural Network to Recognize Hand Gestures." AAAI Conference on Artificial Intelligence, 2018. doi:10.1609/AAAI.V32I1.11400

Markdown

[Giusti et al. "Introducing Machine Learning Concepts by Training a Neural Network to Recognize Hand Gestures." AAAI Conference on Artificial Intelligence, 2018.](https://mlanthology.org/aaai/2018/giusti2018aaai-introducing/) doi:10.1609/AAAI.V32I1.11400

BibTeX

@inproceedings{giusti2018aaai-introducing,
  title     = {{Introducing Machine Learning Concepts by Training a Neural Network to Recognize Hand Gestures}},
  author    = {Giusti, Alessandro and Huber, David and Gambardella, Luca Maria},
  booktitle = {AAAI Conference on Artificial Intelligence},
  year      = {2018},
  pages     = {7950-7951},
  doi       = {10.1609/AAAI.V32I1.11400},
  url       = {https://mlanthology.org/aaai/2018/giusti2018aaai-introducing/}
}