BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:LSTM and Recurrent Neural Networks - Shixiang Gu\; Andrey Malinin
DTSTART:20141120T150000Z
DTEND:20141120T163000Z
UID:TALK55677@talks.cam.ac.uk
CONTACT:39777
DESCRIPTION:Long Short-Term Memory (LSTM) is a type of Recurrent Neural Ne
 twork (RNN) that has recently succeeded in many sequence learning tasks\, 
 such as speech recognition\, online handwriting recognition\, and statisti
 cal machine translation. RNN\, a very deep neural network with many tied w
 eights\, exhibits vanishing or exploding gradient problems common in deep 
 models trained through backpropagation algorithm (BP). LSTM resolves this 
 problem by introducing internal cell memory and access control gates\, ena
 bling learning long temporal range dependencies. In this talk\, we introdu
 ce basics in RNN and LSTM\, and recent successes achieved by LSTM models.
LOCATION:Engineering Department\, CBL Room 438
END:VEVENT
END:VCALENDAR