Reptile: A Scalable Meta-Learning Algorithm

Reptile: A Scalable Meta-Learning Algorithm

  • March 12, 2018
Table of Contents

Reptile: A Scalable Meta-Learning Algorithm

We’ve developed a simple meta-learning algorithm called Reptile which works by repeatedly sampling a task, performing stochastic gradient descent on it, and updating the initial parameters towards the final parameters learned on that task. This method performs as well as MAML, a broadly applicable meta-learning algorithm, while being simpler to implement and more computationally efficient.

Source: openai.com

Tags :
Share :
comments powered by Disqus

Related Posts

The forgetting curve explains why humans struggle to memorize

The forgetting curve explains why humans struggle to memorize

Learning has an evolutionary purpose: Among species, individuals that adapt to their environments will succeed. That’s why your brain more easily retains important or surprising information: It takes very little effort to remember that the neighbor’s dog likes to bite. Remembering the dog’s name is harder.

Read More
Nanowire arrays restore vision in blind mice

Nanowire arrays restore vision in blind mice

Retina is an important light-sensitive tissue that transduces light information into neural activities through multi-layers of neuronal cells. Light entering an eye passes through the transparent retina and is mostly captured by the visual pigment-containing photoreceptors. Retinal degenerative diseases such as retinitis pigmentosa and macular degeneration lead to irreversible damage or even loss of photoreceptors, which can result in serious impairment of vision and eventually blindness.

Read More