{"_id":"6985","status":"public","abstract":[{"text":"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 methods. The ranked contribution of individual cells to the network's output is computed by analyzing a set of interpretable metrics of their decoupled step and sinusoidal responses. As a result, our method is able to uniquely identify neurons with insightful dynamics, quantify relationships between dynamical properties and test accuracy through ablation analysis, and interpret the impact of network capacity on a network's dynamical distribution. Finally, we demonstrate the generalizability and scalability of our method by evaluating a series of different benchmark sequential datasets.","lang":"eng"}],"publisher":"IEEE","author":[{"last_name":"Hasani","full_name":"Hasani, Ramin","first_name":"Ramin"},{"full_name":"Amini, Alexander","last_name":"Amini","first_name":"Alexander"},{"first_name":"Mathias","full_name":"Lechner, Mathias","last_name":"Lechner","id":"3DC22916-F248-11E8-B48F-1D18A9856A87"},{"first_name":"Felix","last_name":"Naser","full_name":"Naser, Felix"},{"full_name":"Grosu, Radu","last_name":"Grosu","first_name":"Radu"},{"first_name":"Daniela","last_name":"Rus","full_name":"Rus, Daniela"}],"publication":"Proceedings of the International Joint Conference on Neural Networks","department":[{"_id":"ToHe"}],"type":"conference","user_id":"2DF688A6-F248-11E8-B48F-1D18A9856A87","day":"30","main_file_link":[{"open_access":"1","url":"https://arxiv.org/abs/1809.03864"}],"year":"2019","oa":1,"publication_identifier":{"isbn":["9781728119854"]},"title":"Response characterization for auditing cell dynamics in long short-term memory networks","language":[{"iso":"eng"}],"date_created":"2019-11-04T15:59:58Z","conference":{"location":"Budapest, Hungary","start_date":"2019-07-14","end_date":"2019-07-19","name":"IJCNN: International Joint Conference on Neural Networks"},"date_updated":"2021-01-12T08:11:19Z","external_id":{"arxiv":["1809.03864"]},"date_published":"2019-09-30T00:00:00Z","publication_status":"published","month":"09","citation":{"short":"R. Hasani, A. Amini, M. Lechner, F. Naser, R. Grosu, D. Rus, in:, Proceedings of the International Joint Conference on Neural Networks, IEEE, 2019.","ista":"Hasani R, Amini A, Lechner M, Naser F, Grosu R, Rus D. 2019. Response characterization for auditing cell dynamics in long short-term memory networks. Proceedings of the International Joint Conference on Neural Networks. IJCNN: International Joint Conference on Neural Networks, 8851954.","mla":"Hasani, Ramin, et al. “Response Characterization for Auditing Cell Dynamics in Long Short-Term Memory Networks.” Proceedings of the International Joint Conference on Neural Networks, 8851954, IEEE, 2019, doi:10.1109/ijcnn.2019.8851954.","chicago":"Hasani, Ramin, Alexander Amini, Mathias Lechner, Felix Naser, Radu Grosu, and Daniela Rus. “Response Characterization for Auditing Cell Dynamics in Long Short-Term Memory Networks.” In Proceedings of the International Joint Conference on Neural Networks. IEEE, 2019. https://doi.org/10.1109/ijcnn.2019.8851954.","ieee":"R. Hasani, A. Amini, M. Lechner, F. Naser, R. Grosu, and D. Rus, “Response characterization for auditing cell dynamics in long short-term memory networks,” in Proceedings of the International Joint Conference on Neural Networks, Budapest, Hungary, 2019.","ama":"Hasani R, Amini A, Lechner M, Naser F, Grosu R, Rus D. Response characterization for auditing cell dynamics in long short-term memory networks. In: Proceedings of the International Joint Conference on Neural Networks. IEEE; 2019. doi:10.1109/ijcnn.2019.8851954","apa":"Hasani, R., Amini, A., Lechner, M., Naser, F., Grosu, R., & Rus, D. (2019). Response characterization for auditing cell dynamics in long short-term memory networks. In Proceedings of the International Joint Conference on Neural Networks. Budapest, Hungary: IEEE. https://doi.org/10.1109/ijcnn.2019.8851954"},"doi":"10.1109/ijcnn.2019.8851954","scopus_import":1,"quality_controlled":"1","oa_version":"Preprint","article_number":"8851954"}