OUR TECHNOLOGY

Bayesian Program Synthesis (BPS)

RECOGNIZING DRAWINGS: DEEP LEARNING VERSUS BPS

In this video, we compare Gamalon’s new Bayesian Program Synthesis (BPS) technology versus state-of-the-art deep learning while playing Pictionary: we draw something, and the system must guess what we drew.

We show that the Gamalon BPS system learns from only a few examples, not millions. It can learn using a tablet processor, not hundreds of servers. It learns right away while we play with it, not over weeks or months. And it learns from just one person, not from thousands. Someday soon you might even have your own private machine intelligence running on your mobile device!



Read more

BPS USES FAR FEWER TRAINING EXAMPLES THAN DEEP LEARNING

Recognizing abbreviations is a problem that comes up a lot in enterprise data, and it is essentially a machine translation task, similar to translating from, say, English to French. In this task, the system sees an abbreviation like “MA” and then must guess “Massachusetts”. We show that compared to state-of-the-art deep learning, Gamalon’s Bayesian Program Synthesis (BPS) requires vastly fewer training examples.

Predictive Accuracy vs Training Examples
Read more

DEEP LEARNING IS PTOLEMY. BPS IS COPERNICUS.

Aristotle created one of the earliest models of the solar system, with the Earth (blue circle) at the center of the solar system, and with Mars (red circle) and the Sun (yellow circle) orbiting around the Earth on circular paths. The predictions from this model (black line in top cells of the video) does not fit the actual observed motion of Mars in the night sky very well. If we plot Mars’ location (declination) in the night sky versus time (red line in top cells of the video), Mars does not cycle up and down in a smooth wave, but exhibits “retrograde motion”; basically it wiggles.

Ptolemy tried to improve upon Aristotle’s model of the solar system to explain the retrograde motion of Mars. Ptolemy kept the Earth in the center of the solar system, but he proposed that Mars goes around an invisible point, in a circle called an “epicycle”, and then this point goes around the Earth. Such a model does exhibit some wiggles. In fact, if you propose that Mars is going around a second invisible point, which orbits the first invisible point, then Ptolemy’s model becomes more accurate. The more epicycles we add, the better it gets. (Mathematically, the multiple epicycle version of Ptolemy’s model is a universal approximator for smooth L2 functions, which fits a series of sinusoids to the observed data. Deep learning models are also L2 smooth function approximators, they just uses sigmoids instead of sinusoids for their nonlinearity.)

Just like deep learning, given enough training data and enough epicycles, Ptolemy’s model will fit the observed motion and also predict the future motion of Mars just as accurately as our modern model of the solar system; but even though it can predict the data with perfect accuracy, you still would not teach Ptolemy’s model to your children… Why not?

Read more

TEACHING ML/AI WITH BOTH DATA AND RULES

The world of machine intelligence is full of different approaches, contradictory ideas, and trendy systems. Let’s take a short walk through some of the big ideas to show you where Bayesian Program Synthesis (BPS) fits in.

Deep learning, neural networks, and regression are all examples of machine learning systems. They learn from labeled training examples. Essentially, a human points at, say, a picture of a chair, and says “chair.” Then the human must repeat this at least 10,000 times with 10,000 different chairs in order to teach the machine what a chair looks like. And then the human must repeat the process for kittens, marmalade, binoculars, and everything else in existence.

Read more

TEDx BOSTON: WHEN MACHINES HAVE IDEAS

Our CEO, Ben Vigoda, gave a talk at TEDx Boston 2016 called “When Machines Have Ideas” that describes why building “stories” (i.e. Bayesian generative models) into machine intelligence systems can be very powerful.


TALKING MACHINES INTERVIEW WITH BEN VIGODA

Listen to Katherine Gorman interview our CEO, Ben Vigoda, on Talking Machines.