This paper presents reinforcement learning with a Long ShortTerm Memory recurrent neural network: RL-LSTM. Model-free RL-LSTM using Advantage( ) learning and directed exploration can solve non-Markovian tasks with long-term dependencies between relevant events. This is demonstrated in a T-maze task, as well as in a di cult variation of the pole balancing task.

We propose a novel supervised learning technique for summarizing videos by automatically selecting keyframes or key subshots. Casting the problem as a structured prediction problem on sequential data, our main idea is to use Long Short-Term Memory (LSTM), a special type of recurrent neural networks to model the variable-range dependencies entailed in the task of video summarization. Our learnin...

Recently, neural networks have been used for not only phone recognition but also denoising and dereverberation. However, the conventional denoising deep autoencoder (DAE) based on the feed-forward structure is not capable of handling very long speech frames of reverberation. LSTM can be effectively trained to reduce the average error between the enhanced signal and the original clean signal by ...

The chain-structured long short-term memory (LSTM) has showed to be effective in a wide range of problems such as speech recognition and machine translation. In this paper, we propose to extend it to tree structures, in which a memory cell can reflect the history memories of multiple child cells or multiple descendant cells in a recursive process. We call the model S-LSTM, which provides a prin...

This study used keyword method during encoding information in transferring information from short term memory to make the retrieval easier. For this purpose, 50 adult female elementary students were chosen to participate in this study. This study required two groups of learners (control and experimental groups). The experimental group enjoyed some special flashcards which each of them involved ...

Games provide the perfect test bed for measuring the effectiveness of computer generated strategies in a competitive and fun environment. Over the years many different games have been tackled by researchers of computational intelligence with the purpose of creating an intelligent computer player that can challenge human players. In this paper the authors summarize the research performed over th...

Associative memory using fast weights is a short-term memory mechanism that substantially improves the memory capacity and time scale of recurrent neural networks (RNNs). As recent studies introduced fast weights only to regular RNNs, it is unknown whether fast weight memory is beneficial to gated RNNs. In this work, we report a significant synergy between long short-term memory (LSTM) networks...