Machine learning is a set of techniques that can reveal hidden patterns in data, and allows you to make predictive systems that grow ever more accurate the more data they learn from. Join us for two insightful workshops on machine learning and Python hosted by SSA Vic and Eliiza.
Getting started with Machine Learning will cover the concepts and workflows involved in constructing these models. Getting started with TensorFlow will involve a deeper look into deep learning and the TensorFlow software framework, including the unique challenges involved in working with such models.
Getting started with Machine Learning
Morning workshop (9am to 12:30pm), presented by Patrick Robotham
This is a hands-on course for making predictive models using machine learning. We will use Python libraries such as pandas and scikit-learn to analyse a dataset and make a predictive model. We will then discuss ideas such as the bias-variance tradeoff for improving machine learning models and apply it to the models built earlier. Throughout the workshop you will program a sequence of Jupyter notebooks and gain experience in working with data in Python. The workshop will conclude with a discussion of how to deploy machine learning models into real world systems.
At the end of this workshop you will be able to:
- Use the Python libraries pandas and numpy to import and manipulate data
- Use scikit-learn to construct linear and tree-based models
- Know the difference between classification and regression
- Evaluate a predictive model with appropriate metrics and plots
- Improve a machine learning model using hyperparameter tuning.
Getting started with TensorFlow
Afternoon workshop (1:30pm to 5pm), presented by Patrick Robotham
Neural networks are a family of machine learning models that can take data in a wide variety of formats and learn non-linear patterns in data by training millions of parameters simultaneously. Neural networks, also known as “Deep Learning”, have become more popular since they were used to win the 2012 ImageNet Challenge. This workshop will teach you how to use the TensorFlow framework to construct neural networks and apply them to tasks such as image recognition.
The workshop will cover:
- The backpropagation algorithm
- The keras functional API
- Convolutional Neural Networks
- Recurrent Neural Networks
- Data representation of images and sound
- Deploying networks into production.
At the end of the workshop you will be able to:
- Train a neural network to recognise images
- Implement neural network papers
- Develop your own neural network architectures for your problem
- Apply machine learning workflows to deep learning.
About the presenter
Patrick Robotham is a Data Scientist working for Eliiza. He regularly develops machine learning models for clients to solve business problems. He has 5 years of professional data science experience and works with RMIT Online as a mentor teaching Introductory AI courses.
- Basic knowledge of Python will be assumed. We expect you to know how to write basic Python functions.
- You will need to bring your own laptop (with administrative rights) to the workshops.
Eliiza, Level 2, 452 Flinders Street, Melbourne
||Full day (both workshops)
||Half-day (1 workshop)
Member prices are available to SSA members or employees and special guests of the Mantel Group. Lunch will be provided for all participants.
Cancellations received prior to 11 Nov 2019 will be refunded, minus a $20 administration fee. From 11 Nov 2019 onwards, no part of the registration fee will be refunded.