Jay van Zyl @ ecosystem.Ai

Jay van Zyl @ ecosystem.Ai

Proximal Policy Optimization

We’re releasing a new class of reinforcement learning algorithms, Proximal Policy Optimization (PPO), which perform comparably or better than state-of-the-art approaches while being much simpler to implement and tune. PPO has become the default reinforcement learning algorithm at OpenAI because of its ease of use and good performance.

PPO

Better healthcare with machine learning

I was traveling to a remote area in India couple of weeks ago. And I visited a govt hospital to see someone I know. As we all know the pathetic condition of govt hospitals in India especially in a remote area.

One of the issues is the availability of doctors and medical equipment.

The employment of doctors is based on the population of an area and finding specialists like cardiologists, nephrologist, pediatrics, etc is next to impossible.

I work as a software engineer…

Robust Adversarial Examples

We’ve created images that reliably fool neural network classifiers when viewed from varied scales and perspectives. This challenges a claim from last week that self-driving cars would be hard to trick maliciously since they capture images from multiple scales, angles, perspectives, and the like.


*This innocuous kitten photo, printed on

Robust Adversarial Examples

We’ve created images that reliably fool neural network classifiers when viewed from varied scales and perspectives. This challenges a claim from last week that self-driving cars would be hard to trick maliciously since they capture images from multiple scales, angles, perspectives, and the like.


*This innocuous kitten photo, printed on

Imagine this: Creating new visual concepts by recombining familiar ones

Around two and a half thousand years ago a Mesopotamian trader gathered some clay, wood and reeds and changed humanity forever. Over time, their abacus would allow traders to keep track of goods and reconcile their finances, allowing economics to flour…