Duration: 1 day

Recent developments in machine learning approaches, collectively referred to as deep learning, are responsible for the large performance gains made in the last decade in tasks such as voice recognition, image and video classification, and forecasting. Deep learning refers to a relatively recent set of generative machine learning techniques that autonomously generate high-level representations from raw data sources, and using these representations perform machine learning tasks such as classification, regression, and clustering.  Through real world examples, discussions, and live code demonstrations this one-day workshop designed for analytics professionals introduces the most important deep learning techniques for supervised and unsupervised machine learning tasks.

At Course Completion:

This workshop has been designed to equip delegates with the most important deep learning techniques, and an understanding of how they should be applied to build real-world-relevant solutions. After completing the workshop delegates will be able to:

  • Frame business problems as deep learning problems and solve them using appropriate techniques
  • Understand the basic structure of artificial neural networks
  • Understand gradient descent and the back-propagation of error algorithm
  • Appreciate the complications involved in building deep neural networks
  • Understand how to apply appropriate deep learning techniques (e.g. convolutional neural networks) to image understanding problems (e.g. classification and segmentation)
  • Understand how to apply appropriate deep learning techniques (e.g. recurrent neural networks) to text understanding problems (e.g. classification and translation)

Course Outline:

  • Introduction and machine learning refresher
  • Introducing loss functions, optimization, neural networks, gradient descent, and the back-propagation of error algorithm
  • Building and deploying deep feed-forward neural networks (with technology introduction)
  • Demonstration: Building deep neural networks

 

  • Using convolutional neural networks for image understanding problems
  • Demonstration: Building convolutional networks for image understanding problems
  • Utilising different network layers, dropout, batch normalization
  • Demonstration: Optimising models for image understanding problems

 

  • Representing text using word vector embeddings
  • Demonstration: Utilising word vector embeddings
  • Using deep neural networks for text understanding problems
  • Demonstration: Building text understanding models
  • Future directions in deep learning
Fundamentals of Machine Learning for Predictive Data Analytics

Prerequisites:

To attend this course delegates should be familiar with fundamental concepts in data manipulation, descriptive statistics, and machine learning. Specifically, delegates should be comfortable building and evaluating classification models (using techniques such as logistic regression, decision trees, support vector machines or random forests).

Demonstrations:

The live code demonstrations during the workshop will use the Python programming language and relevant Python packages (e.g. pandas, scikit-learn, and keras). While familiarity with these is not required it would be useful. A list of specific functionality with which delegates should be familiar, and suggested online revision materials, will be circulated to delegates before the workshop.

Download Info PDF

About The Trainers

Dr. Brian Mac Namee
Dr. Brian Mac Namee
Dr. Brian Mac Namee, Director of Training at the Analytics Store, has over 14 years experience in analytics lecturing, training, and consultancy. He received a BA (mod) and PhD in Computer Science from Trinity College Dublin in 2000 and 2004 respectively. After a period working in industry as an R & D software engineer for Agilent Technologies, Brian joined the School of Computing at Dublin Institute of Technology as a lecturer in 2005. At DIT Brian co-founded the Applied Intelligence Researcher Centre (www.ditairc.ie), and developed DIT’s successful MSc in Computing (Data Analytics) programme. In 2015 Brian joined the UCD School of Computer Science as a lecturer where he is a Principal Investigator at the CeADAR centre (www.ceadar.ie) and a Funded Investigator at the Insight centre (www.insight-centre.org). Brian’s research focuses on machine learning, predictive analytics, data visualisation, and augmented reality. Brian has published extensively in machine learning, predictive analytics, and information visualisation – a recent highlight is the textbook “Fundamentals of Machine Learning for Predictive Data Analytics: Algorithms, Worked Examples and Case Studies” published with MIT Press in 2015 (www.machinelearningbook.com).