Response Characterization for Auditing Cell Dynamics in Long Short-term Memory Networks
In this paper, we introduce a novel method to interpret recurrent neural networks (RNNs), particularly long short-term memory networks (LSTMs) at the cellular level. We propose a systematic pipeline for interpreting individual hidden state dynamics within the network using response characterization...
Main Authors: | Hasani, Ramin (Author), Amini, Alexander A (Author), Lechner, Mathias (Author), Naser, Felix M (Author), Grosu, Radu (Author), Rus, Daniela L (Author) |
---|---|
Other Authors: | Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory (Contributor), Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science (Contributor) |
Format: | Article |
Language: | English |
Published: |
Institute of Electrical and Electronics Engineers (IEEE),
2021-05-04T14:56:09Z.
|
Subjects: | |
Online Access: | Get fulltext |
Similar Items
-
Adversarial Training is Not Ready for Robot Learning
by: Lechner, Mathias, et al.
Published: (2022) -
Audit of long-term and short-term liabilities
by: Korinko M.D., et al.
Published: (2017-03-01) -
Short-long-term memory interaction with underlearned long term storage.
by: Fergenson, P. Everett
Published: (1965) -
Short-term Load Forecasting with Clustering and Long-Short Term Memory Model
by: Meng-Hsuan Lee, et al.
Published: (2019) -
Short-Term Electric Load Forecasting Model Using Long Short-Term Memory
by: HUANG,JIAN-KAI, et al.
Published: (2019)