If you want to train a machine learning model on a large dataset such as ImageNet, especially if you want to use GPUs, you’ll need to think about how you can stay within your GPU or CPU’s memory limits. Generators are a great way of doing this in Python. What is a generator? A generator is a function that behaves … Read More
Machine Learning resource: Chris Albon’s Code Snippets and Flashcards
I was looking for code to implement early stopping in Keras today and came across Chris Albon’s website. You may know Chris as a host of Partially Derivative, a podcast about data science. Chris has posted many snippets of commented recipe-like code to do simple things on his website. These range from ways to preprocess images, text and dates such … Read More
AlphaGo Zero: An overview of the algorithm
In this post I go through the algorithms presented in the groundbreaking AlphaGo Zero paper using pseudocode. The objective is to provide a high-level idea of what the model does. Why AlphaGo Zero matters Last week, Google DeepMind published their final iteration of AlphaGo, AlphaGo Zero. To say its performance is remarkable is an understatement. AlphaGo Zero made two breakthroughs: … Read More
How I completed Udacity’s Machine Learning ND in just over one month
How can we learn more effectively in a short amount of time? In this post, I describe how I went about finishing Udacity’s Machine Learning Nanodegree in about a month when it usually takes 6-12 months. I hope this will give you some insight and ideas as to how you might work more effectively to accomplish your own learning goals. Sections in … Read More
Code, Explained: Training a model in TensorFlow
In a previous post, we went through the TensorFlow code for a multilayer perceptron. Now we will discuss how we train the model with TensorFlow, specifically in a TensorFlow Session. We will use Aymeric Damien’s implementation in this post. I recommend you skim through the code first and have the code open in a separate window. I have included the key portions … Read More
Machine Learning in Trading – Project Takeaways
People have used machine learning in trading for decades in order to learn how to be successful at online stock trading. Hedge funds, high-frequency trading shops and sole traders use all sorts of strategies, from Bayesian statistics to physics related strategies. In my final project for Udacity’s Machine Learning Nanodegree, I investigating using machine learning in trading stocks, specifically to … Read More
Questions to ask when deciding how to approach predictive problems
Is the situation stochastic or deterministic? Is it time-inhomogeneous? (Different across time?) How much data do you have available? What limitations are there with respect to computational cost (compute and time), both for training and predicting? Do you need to try actions to learn about situations? (If so, consider Reinforcement Learning.) Do your actions have an impact on the environment? … Read More
Udacity Connect Review (London)
Udacity Connect are in-person meet-ups to supplement Udacity’s Nanodegrees, online certifications that consist of a series of courses and graded projects. (Udacity is an online educational organisation that offers technology-centred online courses.) After piloting in the US over the summer, Udacity Connect launched in London last week. In this post I describe what happened at the second(my first) Machine Learning … Read More
Artificial Intelligence at Apple
A summary of the article ‘An Exclusive Look at how AI and Machine Learning work at Apple’ by Steven Levy posted on Backchannel. Apple has been keeping a low profile on its artificial intelligence developments, so much so that critics thought it was far behind companies such as Facebook and Google. In this interview, Apple executives discuss how sophisticated Artificial … Read More
Multi-label classification: One debating topic, many categories
What colour is this rainbow? Yesterday we wrangled debating motions data using Google Sheets. Today we’ll discuss building a machine learning model to classify these debating topics (e.g. This House Would Break Up the Eurozone) into categories (e.g. ‘Economics’ and ‘International Relations’). Why is this problem interesting? It is primarily a text classification problem. It is a multi-label classification problem. … Read More