Deep Learning and Applications

Introduction to deep learning and neural networks. Applying deep learning models to make predictions with text and images. feed forward neural networks, convolutional neural networks, recurrent neural networks. Backpropogation.

Duration

15 to 25 h

Syllabus

Introduction to Neural Networks and related optimization methods

Deep Neural Network architectures (convolutional, recurrent, 
multilayer, autoencoders) and implementation with Keras and/or Pytorch (Python)

• Tensor Factorization, Factorization Machines
• Deep Collaborative Filtering techniques such as Autoencoders for Collaborative Filtering, RNN’s for session-based recommendations and convolutional networks for feature extraction

Deep Learning for building recommender systems:

• Tensor Factorization, Factorization Machines
• Deep Collaborative Filtering techniques such as Autoencoders for Collaborative Filtering, RNN’s for session-based recommendations and convolutional networks for feature extraction

Natural Language Processing with Deep Learning:

• language modeling
• word and document embeddings
• conversational models and visualization

Generative adversarial networks and other advanced Deep Learning concepts

Prerequisites

Foundations of Data Science

Credential

Summer School Week III, part of Computational Machine Learning course in MSc in Data Science, DSC workshops, executive (ad-hoc) trainings