Duration : 4 Days
Overview : This course focuses on using machine learning techniques based on large artificial neural networks to perform prediction and generation tasks. These are often referred to as deep learning models and their introduction in recent years, coupled with advances in computational hardware and the scale of datasets currently available to us, has led to step changes in the performance of machine learning models. This course has been designed to guide delegates through the most important topics in deep learning, and how they should be applied to build real-world-relevant solutions. This course is delivered in Python.
At Course Completion : After attending this course, 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)
- Use an appropriate deep learning technology to build and deploy deep learning models
Who Should Attend : This course is relevant to people who are working with data analytics and machine learning techniques but would like to harness the potential of more recent deep learning techniques. This course is ideally suited to people working in data analyst, data science, business analyst, statistician, or similar roles.
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). In addition, delegates should be capable of writing code in the Python programming language. In particular delegates should be comfortable performing data manipulation with the pandas package and performing machine learning tasks using the scikit-learn package.
Outline : The course will run over four days and will broadly follow the timetable shown below. The course will be delivered through presentations, real world examples, discussions, and workshops.