scispace - formally typeset
Search or ask a question

Answers from top 12 papers

More filters
Papers (12)Insight
Thus, one neuron or group of neurons anywhere in the cortex can be a part of many networks and thus many memories.
Open accessPosted ContentDOI
Shailee Jain, Alexander G. Huth 
21 May 2018-bioRxiv
97 Citations
These results suggest that LSTM language models learn high-level representations that are related to representations in the human brain.
Simulation studies will be presented to demonstrated the new LSTM structure performs much better than conventional RNN and even single LSTM network.
Another advantage of the LSTM-RNN is that it can also be used with measurements that include transitions between classes over time.
We find that neurons with spike-frequency adaptation, which occur especially frequently in higher cortical areas of the human brain, provide to brains a functional equivalent to LSTM units.
Open accessProceedings ArticleDOI
Fei Tao, Gang Liu 
15 Apr 2018
40 Citations
The A-LSTM outperforms the conventional LSTM by 5.5% relatively.
Proceedings ArticleDOI
Zaifa Chen, Yancheng Liu, Siyuan Liu 
26 Jul 2017
43 Citations
It shows that LSTM is superior in machine state prediction and monitoring.
Compared with other conventional models, ST-LSTM network can achieve a better performance in experiments.
Our results show that the low level combination works best, thanks to the powerful data modeling of the LSTM neurons.
The results show that the proposed methods are more accurate than a normal LSTM model.
Experiment results show the standard LSTM outperformed others.
Open accessProceedings ArticleDOI
Fei Tao, Gang Liu 
15 Apr 2018
40 Citations
This shows the advantage of A-LSTM.