When I hear the word “ensemble”, I think of two things: the grand canonical ensemble, and the brass ensemble. But today we’re taking a look at ensemble learning, which is the canonical way that the grand top brass of data scientists augment and combine models. The need for ensembling arises when you’re working at the cutting edge and a good model is not available. One model might anticipate a fraction of the cases, another a different fraction, and a
Blog Posts
Melbourne (21 August 2017) – Consilium Technology Pty Ltd (Consilium), an Australian Machine Intelligence Business and Research Services Provider, are exhibiting their machine intelligence and simulation capability at the International Joint Conference on Artificial Intelligence (IJCAI). The conference is being held from 21-24 August at the Melbourne Exhibition and Conference Centre. Dr Sebastien Wong (Director of Machine Learning, Consilium): “Our goal is to help businesses leverage advances in machine learning. We were founded in 2010 to service defence research
I spent last Thursday engaging as a mentor to teams in the Adelaide Techstars start-up accelerator. Having been busy with other projects leading up to the event, I hadn’t thought deeply about Techstars, and as a result I didn’t have many preconceptions about what was expected from the mentoring process. Having worked primarily in government and academic R&D labs for 18 years, and only engaging with the commercial business world for the last two years, I wondered about the
My parents, hoping to encourage a career in medicine, gave me a book on the human body for my sixth birthday. This was just after the release of the original Starwars movie and the book used robots as an analogy to describe the functions of the body. I remember the picture of the brain being a computer and connected to the sensory inputs through wires. Unbeknownst to them, my parents had started me down the path of becoming an
Sometimes, it’s risky to explore the realms of possibility. Machine Intelligence offers promises of prediction, actionable insight, intelligent automation. You most likely question the authenticity of these claims. Could it really make a difference to your bottom line? Most likely your perception of what is possible is limited. Your reference points of what’s proven in the industry are narrow. You are naturally sceptical. When you deliberately set out to explore, one of two things happen, you prove your suspicions or
Feature learning will allow machine learning to revolutionize many industries, without needing years of domain expertise. “What is a good feature?” This is a three-decade old question in machine learning. Before we can understand the question, we must first understand what is a feature. In machine learning, features are any observations of a sample that are used to make a prediction or classification. For example, consider the problem of estimating the age of a child (our sample) using a
Let There be a Lighthouse In the preceding post we attempted to locate a queer lighthouse from the incident locations of its angularly uniformly distributed flashes upon a straight beach. The geometry of the scenario is shown below. It turned out to be a difficult problem, because the flashpoints assume a Cauchy distribution, which makes the intuitively appealing sample mean totally useless. In this post, we track down the lighthouse by applying sound principles of probability theory which are commonly
A Light Under a Bushel You’re walking along a straight beach at night and you happen to know there’s a lighthouse somewhere out to sea, shrouded in darkness on a rocky island. But it is no ordinary lighthouse: it emits flashes in random directions, favouring no angle over any other. Fortuitously, you have a set of sensors rigged up along the coastline that register the incident locations of any flashes that hit the beach. Where is the lighthouse? It
… continued from part 1 Data Augmentation with SMOTE What about the case when we dont know how to peturb the data to ensure that label information is preserved? Well the Synthetic Minority Over Sampling Technique (SMOTE) can be used. Imagine every sample is a point in a multi-dimensional graph, where each dimension of the graph is one of the features. This is commonly referred to as feature space. Select two random samples fromthe same class. Now imagine drawing
One of the key components to a successful machine learning product is having sufficient, good quality data to train the classifier. The data samples should be representative of the entire population distribution. Increasing the number of samples reduces the risk of your model over fitting the data. That is, the model is too complex for the data set. The best way to get more samples is to simply go out and collect them. This might mean expensive and time