Machine learning (ML) is a sub-field of Artificial Intelligence. ML itself is a very broad field and includes subjects like deep-learning and reinforcement learning and can be considered the current practical side of AI.
We cover pretty much the whole field of ML but we have a strong focus on deep learning and generative techniques.
Perth Machine Learning Group is dominantly a coding group, oriented towards helping people understand, code and implement practical machine learning solutions. Members are diverse coming from across industry, academia, government and the startup community. We provide around two hours of practical talks and learning support every week, covering topics from beginner to bleeding edge AI. We also provide support for sponsoring companies (like Western Power) to build organisation capability and increase the level of engagement in training.
Most meetings have a high level of community engagement. Learning is loosely wrapped around the FAST.AI online curriculum and M...
There are some great online demos which let you simply play with the ideas without getting into the details
Why is this important?
Engaging your imagination and curiosity is one of the greatest tools you have to help you succeed.
Find your style of learning
There are many courses out there and your style of learning maybe more or less suited to the different approaches they use.
We primarily recommend Fast.ai because of their practice hands on approach. If you are a profession who already has domain expertise in some other field and just want to add on new tools, this can be a great way to go and avoids getting bogged down in deep academic analysis of specific algorithmic implementation.
Ultimately you will be learning about a very cross disciplinary field and you will end up looking at the intersection of your own field with data analytical methods, programming and mathematics.
In this light it is well worth taking some priming courses
John Vial is a cofounder of the Perth Machine Learning Group, he has a PhD in Robotics from the University of Sydney and can often be found teaching beginners deep learning and walking the group through the lessons of the fast.ai deep learning course.
John is also CEO of SounDelve, a machine learning consultancy focused on delivering solutions into the mining industry.
The quest for automatically tracking electrical appliance use
At Western Power, we are beginning to apply machine learning techniques in a bid to improve efficiency. So far, there have been several successful test cases:
Identifying conductor defects using the DataRobot platform
Detecting solar PV installations from aerial photographs using Convolutional Neural Networks
Predicting power pole top fires using decision trees and Xgboost
In this use case, we are attempting to identify electrical appliances being utilised behind customer meters from high frequency interval meters. That is, electricity meters that record the amount of kilowatt hours of electricity consumed at daily, hourly and five minute intervals.
A few reasons for attempting this are:
We can help manage critical peak demand periods by identifying areas of demand that exceed local network constraints.
Help customers understand which appliances are contributing the most to their utility bill. This info...