IJSR - International Journal of Scientific Research

Ms. Archana Gopnarayan; Prof. Sachin Deshpande

Volume : VIII, Issue : VI, June - 2019

Survey of Prediction using Recurrent Neural Network with Long Short–Term Memory

Ms. Archana Gopnarayan, Prof. Sachin Deshpande

Abstract :

Sequence prediction problems are major problem from long time. From predicting sales price, movie plots, speech recognizing, predicting next word on the Phone’s keyboard and match results. With the recent eakthroughs that have been happening in data science, it is found that for almost all of these sequence prediction problems, Long Short Term Memory is most effective solution .LSTM have an edge over feed–forward neural networks and RNN in many ways. This is because of selectively remembering patterns for long durations of time. LSTM enable RNN to remember their inputs over a long period of time. This is because LSTM contain their information in a memory that is much like the memory of a computer because the LSTM can read, write and delete information from its memory.