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

Authors

  • Alessandro Giusti Dalle Molle Institute for Artificial Intelligence (IDSIA), USI-SUPSI, Lugano
  • David Huber Dalle Molle Institute for Artificial Intelligence (IDSIA), USI-SUPSI, Lugano
  • Luca Gambardella Dalle Molle Institute for Artificial Intelligence (IDSIA), USI-SUPSI, Lugano

DOI:

https://doi.org/10.1609/aaai.v32i1.11400

Keywords:

machine learning, computer vision, education, convolutional neural networks, deep learning

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.

Downloads

Published

2018-04-27

How to Cite

Giusti, A., Huber, D., & Gambardella, L. (2018). Introducing Machine Learning Concepts by Training a Neural Network to Recognize Hand Gestures. Proceedings of the AAAI Conference on Artificial Intelligence, 32(1). https://doi.org/10.1609/aaai.v32i1.11400