Access to tutorials includes the possibility of following any tutorial.

Deep learning methods: a practical approach

Francesco Morandin
University of Parma (IT)

Deep learning methods can be effectively used in classification and regression/estimation tasks with high dimensional input, provided that large training data sets are available.

We start with a presentation of classical neural networks concepts: perceptron, multilayer neural networks, backpropagation, stochastic gradient descent, convolutional neural networks. We proceed with recent developments in deep learning, such as unsupervised weight initialization, autoencoders, cross-entropy, dropout. A special focus is given to two tools readily available to the researcher: Tensorflow and Keras.

Practical examples/tasks are given. Further information will be available by the end of June.

Francesco Morandin is associate professor in probability and statistics at SMFI Department of Parma University, with two main research fields: analytical results about shell models of turbulence and applied tasks in data science. Recently he has been working on deep reinforcement learning and leads an inter-university research collaboration that is developing innovative A.I. agents for perfect information games such as Go. He is a member of the Italian Mathematical Olympiad Committee.

Important Dates
  • Paper submission (extended):

    10 May

    26 May

  • Notification of acceptance:

    30 June
  • Camera-ready:

    21 July