Large Scale Deep Learning (repost of presentation by Jeff Dean @ Google)

Screenshot 2014-12-27 10.46.53

Above should not be taken out of context as hubris. There are brute force improvements that cannot be denied. The paradigm called deep learning – uncountable data + many layers of uncountable simple computations – is moving us monotonically closer to AI. Domain specific short-cuts (e.g. human programmed computers) will always have some advantage, but this margin will reduce.

The presentation describes numerous experiments that are showing the efficacy of artificial neural network based inference. These include significant improvements in speech recognition, image labelling, translation and some success in more challenging areas such as analogies.

Leave a Reply

Fill in your details below or click an icon to log in: Logo

You are commenting using your account. Log Out /  Change )

Google photo

You are commenting using your Google account. Log Out /  Change )

Twitter picture

You are commenting using your Twitter account. Log Out /  Change )

Facebook photo

You are commenting using your Facebook account. Log Out /  Change )

Connecting to %s