Deep Learning & Tensorflow

Get your team up to speed with our hands-on comprehensive training on Deep Learning. Based on the materials presented at top academic conferences.

What is it about?

This training will provide an accessible introduction to Neural Networks, Deep Learning, Tensorflow, and key lighthouse applications. It will examine the history of neural networks and the state-of-the-art approaches to deep learning. Participants will learn the theory underlying the core neural network architectures and training procedures. Participants will read current research articles to appreciate the state-of-the-art approaches as well as to question some of the hype that comes with the resurgence of popularity.

Conceptually, the training is divided into two parts. The first part will cover fundamental concepts of neural networks and corresponding learning algorithms building things up from the first principles, demonstrating them with notebooks. The second part will focus on developments in the field of deep learning around word2vec for language embeddings, convolutional neural networks for structured data, recurrent neural networks for sequence data, and autocoders for unsupervised learning. In addition to these algorithms the practical tricks (ReLU activation, dropout, smart gradient descent, and more) needed to get them to work will also be presented. This material will be grounded through implementations in Python and deep learning frameworks (e.g. Keras, Tensorflow), along with applications and case studies in digital advertising, computer vision, natural language processing, and information retrieval. Examples and exercises will be made available in Python notebooks.

Training Content