Tags

, , , , , ,

Screenshot-1

“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 2600 games from the Arcade Learning Environment, with no adjustment of the architecture or learning algorithm. We find that it outperforms all previous approaches on six of the games and surpasses a human expert on three of them”. (1, 2, 3)

Scientists who created a learning algorithm which managed to successfully learn how to play video games. Like a baby learning how to live, machines can do that too. Everything can be learned.

We are all eager to learn. We like it when something/ someone learns. We like to teach someone/ something how to learn. But is life about learning? Is life about adding more data, more information into our brain? Or is it about removing everything from it? If a machine can learn, could it be that humans should not? Consciousness should be free from limitations. And every piece of knowledge poses a new limitation.

Listen to the void.

This is where all knowledge lies…

Unlearn what you have learnt.

Fail to do so and you will soon be inseparable from a machine playing Arcanoid…