Neural Turing Machines


Essentially an architecture with a controller (FNN, RNN, LSTM) that has read/write access to a memory in order to learn a particular task. The controller gets an input, can read/write to memory block and then output a result.

When reading and writing to the memory matrix, introspective attention is used. Separate attention weights for reading, erasing and writing. All of this is end-to-end differentiable, so theoretically we can learn very complex tasks.


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