The Next Input updates
Browse every published The Next Input update in a calm card overview with images, dates, and direct access to each article.
The Next Input update
One-shot imitation learning
Read paper(opens in a new window)
The Next Input update
Distill
We’re excited to support today’s launch of Distill, a new kind of journal aimed at excellent communication of machine learning results (novel or existing).
The Next Input update
Learning to communicate
Title: Learning to communicate
The Next Input update
Emergence of grounded compositional language in multi-agent populations
Read paper(opens in a new window)
The Next Input update
Prediction and control with temporal segment models
Read paper(opens in a new window)
The Next Input update
Third-person imitation learning
Read paper(opens in a new window)
The Next Input update
Attacking machine learning with adversarial examples
Adversarial examples are inputs to machine learning models that an attacker has intentionally designed to cause the model to make a mistake; they’re like optical illusions for machines. In this post we’ll show how adversarial examples work across different mediums, and will discuss why securing systems against them can be difficult.
The Next Input update
Adversarial attacks on neural network policies
Read paper(opens in a new window)
The Next Input update
Team update
Title: Team update
The Next Input update
PixelCNN++: Improving the PixelCNN with discretized logistic mixture likelihood and other modifications
Read paper(opens in a new window)(opens in a new window)
The Next Input update
Faulty reward functions in the wild
Reinforcement learning algorithms can break in surprising, counterintuitive ways. In this post we’ll explore one failure mode, which is where you misspecify your reward function.
The Next Input update
Universe
We’re releasing Universe, a software platform for measuring and training an AI’s general intelligence across the world’s supply of games, websites and other applications.
Showing 1045 to 1056 of 1,127 updates.