Throughout the history of homo sapiens, wars, famine and diseases are the main killing machines.  For the first time, we have recently defeated famine and lost appetite for wars. We now turn our attention to the most basic need of all: health. Who doesn't want to live a healthy life and die in peace? But how do understand a healthcare system, from a modeler point of view? Healthcare is a complex business. A battle field that can determine outcome of election, which may change the course of history. I've always speculated that healthcare is an algebraic system. Medical ..read more

I have dreamed big about AI for the future of healthcare. Now, after just 9 months, it is happening at a fast rate. At the Asian Conference on Machine Learning this year (Nov, 2017) held in Seoul, Korea, I delivered a tutorial covering latest developments on the intersection at the most exciting topic of the day (Deep learning), and the most important topic of our time (Biomedicine). The tutorial page with slides and references is here. The time has come. Stay tuned ..read more

One thing as popular as hydrogen in the universe, is vector. Most mathematical and data analytical analysis asks for this fundamental structure of the world. PCA, ICA, SVM, GMM, t-SNE, neural nets to name a few, all implicitly assume vector representation of data. The power of vector should not be underestimated. The so-called distributed representation, which is rocking the machine learning and cognitive science worlds, is nothing but vector representation of thought (in Geoff Hinton's words, referring to Skip-Thought vectors). The current love for distributed representation of things (ye ..read more

Supervised machine learning has a few recurring concepts: data instance, feature set and label. Often, a data instance has one feature set and one label. But there are situations when you have multi-[X], where X = instance, view (feature subset), or label. For example, in multiple instance learning, you have more then one instance, but only one label. Things are getting interesting when you have multiple instances, multiple views and multiple labels at the same time. For example, a video clip can be considered as a set of video segments (instances), each of which has views (audio, visual fr ..read more

In a not-so-distant future, it will be a routine to chat to a machine and receive medical advice from it. In fact, many of us have done this - seeking advice from healthcare sites, asking questions online and being recommended for known answers by algorithms. The current wave of AI will only accelerate this trend. Medicine is by large a discipline of information, where the knowledge power is very asymmetric between doctors and patients. Doctors do the job well because humans are all alike, so that cases can be documented in medical textbooks and findings can be shared in journal articles a ..read more

Turing machine (aturingmachine.com) It is a coincidence that Big Data and Deep Learning popped up at the same time, roughly around 2012. And it is told that data to deep learning is fuel to rockets (this line is often attributed to Andrew Ng, co-founder of Coursera and Chief Scientist at Baidu). It is true that current deep learning flourishes as it leverages big, complex data better than existing techniques. Equipped with advances in hardware (GPU, HPC), deep learning applications are more powerful and useful than ever. However, without theoretical advances, big data might have rema ..read more

It is hard to imagine a modern life without electronics: radios, TVs, microwaves, mobile phones and many more gadgets. Dump or smart, they are all based on the principles of semi-conducting and electromagnetism. Now we are using these devices for granted without worrying about these underlying laws of physics.  Most people do not care about circuits that run in chips and carry out most functions of the devices. For the past 5 years, a new breed of human-like functionalities has emerged through advances of a new field called deep learning: self-driving cars, voice command in m ..read more

Neil Lawrence had an interesting observation about the current state of machine learning, and linked it to fast ball games: “[…] the dynamics of the game will evolve. In the long run, the right way of playing football is to position yourself intelligently and to wait for the ball to come to you. You’ll need to run up and down a bit, either to respond to how the play is evolving or to get out of the way of the scrum when it looks like it might flatten you.” Neil Lawrence is known for his work in Gaussian Processes and is a proponent of data efficiency. He used to be professor at University of ..read more

I read somewhere, but cannot recall exactly who said so, that in ancient worlds, 30 years are long enough for the new generation to settle down with a new system, regime or ideology. As there are only a few days away from 2017, I would like to look back the history of a 30-year old model which has captured my research attention for the past 10 years. To some of you, restricted Boltzmann machine (RBM) may be a familiar name, especially for those who follow the current deep learning literature since the beginning. But RBM has also passed its prime time, so you may have heard about i ..read more

How can we characterize machine learning as a field? What make machine learning work? Machine learning is a fast changing field. The list of ideas is practically endless: Decision trees, ensemble learning, random forests, boosting, neural networks, hidden Markov models, graphical models, kernel methods, conditional random fields, sparsity, compressed sensing, budgeted learning, multi-kernel learning, transfer learning, co-training, active learning, multitask learning, deep learning, lifelong learning and many more. The problem is, ideas come and go, and bounce back, roughly every 10-15 ye ..read more