This is a presentation given for Data Science DC on Tuesday November 14, 2017. PDF slides PPTX slides Further resources up front: A Brief Survey of Deep Reinforcement Learning (paper) Karpathy’s Pong from Pixels (blog post) Reinforcement Learning: An Introduction (textbook) David Silver’s course (videos and slides) Deep Reinforcement Learning Bootcamp (videos, slides, and labs) OpenAI gym / baselines (software) National Go Center (physical... Read more
Making a machine learning model usually takes a lot of crying, pain, feature engineering, suffering, training, debugging, validation, desperation, testing and a little bit of agony due to the infinite pain. After all that, we deploy the model and use it to make predictions for future data. We can run our little devil on a batch... Read more
A Global Perspective: The Future of Artificial Intelligence
The world is being transformed through rapid breakthroughs in data and AI. Every day, we hear about more innovations — from small startups to global economies. Nearly every job currently occupied by human labour–from farmers, offshore customer service representatives and even taxi drivers–could be given to a robot within the... Read more
Named Entity Recognition: Milestone Models, Papers and Technologies
Named Entity Recognition: Extracting named entities from text Named Entity Recognition (NER), or entity extraction is an NLP technique which locates and classifies the named entities present in the text. Named Entity Recognition classifies the named entities into pre-defined categories such as the names of persons, organizations, locations, quantities, monetary... Read more
GANs explained. Generative Adversarial Networks applied to Generating Images
Editor’s note: Guest post co-writer Keshav Dhandhania.  In this article, I’ll talk about Generative Adversarial Networks, or GANs for short. GANs are one of the very few machine learning techniques which has given good performance for generative tasks, or more broadly unsupervised learning. In particular, they have given splendid... Read more
Bayesian Surprise
For reasons not entirely unconnected with NZ election polling, I’ve been thinking about surprise in Bayesian inference again: what happens when you get a result that’s a long way from what you expected in advance? Yes, your prior is badly calibrated and you should feel bad, but what should... Read more
In a previous article, we discussed the origin story and history of the Python deep learning library TensorFlow. It’s experienced a monumental rise like nothing seen before, in just two years since its debut it currently holds the title of the most forked repo on GitHub. TensorFlow’s significance doesn’t... Read more
UNHCR Refugee Data Visualized
Where’s the Data? The data I’m using is taken from the United Nations High Commissioner for Refugees (UNHCR) website – the UN Refugee Agency. You can read more on what they do and why the exist in the link above.  Currently you can only download the mid-year statistics for 2015. You get a... Read more
A conversation with  Professor Neil Lawrence, Director of Machine Learning at Amazon Research
As the practice of data science and AI evolves and permeates all aspects of society, the need to understand its impact increases. In this wide ranging interview, Professor Neil Lawrence, Director of Machine Learning at Amazon Research, touches on a number of thought provoking topics. Neil discusses the need... Read more
Learning from users faster using machine learning
I had an interesting idea a few weeks ago, best explained through an example. Let’s say you’re running an e-commerce site (I kind of do) and you want to optimize the number of purchases.Let’s also say we try to learn as much as we can from users, both using A/B... Read more