Let's steal nature's design tools.
The first version of Learning Alarm is now live. Using TensorFlow, I implemented a very simple neural network that monitors an alarm clock application and uses reinforcement learning to improve… Read More →
The reinforcement learning problem presented in Learning Alarm is fairly straightforward. Our goal is to learn the best way to wake someone up. Each day, Learning Alarm will try out a… Read More →
More and more people are beginning to use their phones as their alarm clocks and why not? They have a variety of alarm apps they can choose from, set their… Read More →
Nowadays when I look at everyday objects, I think to myself, “If (insert object here) could learn, how would it change the way I interact with it?” One of the… Read More →
Interactions between computers and the physical world are forced and awkward. Robots seem preprogrammed and even the smallest of changes in the environment can trip up machines. In the digital world… Read More →
Harmonic Tracks When racing drivers talk about their favorite race tracks, they are most concerned with the way the track feels to drive. Like all things subjective, its impossible to… Read More →
As I mentioned in the project, ‘Particle Network’ doesn’t even begin to show the potential of what a neural network can do. It is merely a visualization of what happens inside of… Read More →