Category: Learning
-
Learning machines. Unlearning humans. Void. Arkanoid.
"We present the first deep learning model to successfully learn control policies directly from high-dimensional sensory input using reinforcement learning. The model is a convolutional neural network, trained with a variant of Q-learning, whose input is raw pixels and whose output is a value function estimating future rewards. We apply our method to seven Atari…
-
Learning rules. Having false memories...
Our tendency to create false memories could be related to our ability to learn rules according to new research. New research suggests that individuals who are particularly good at learning rules and classifying objects by common properties are also particularly prone to false memory illusions. (1) Forget whatever you have learned. It is the only…
-
Tortoises. Heart. Brain.
Tortoises are using their cleverness to do more than just win long distance races against hares–now they’re moving into the field of touchscreen technology. Researchers from the U.K.'s University of Lincoln have successfully trained four red-footed tortoises (native to Central and South America) to touch different objects on a screen. In a video from the…
You must be logged in to post a comment.