Exploring interpretable LSTM neural networks over multi-variable data
Authors: Tian Guo, Tao Lin, Nino Antulov-Fantulin
ICML 2019 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | Extensive experiments on real datasets demonstrate enhanced prediction performance by capturing the dynamics of different variables. Meanwhile, we evaluate the interpretation results both qualitatively and quantitatively. |
| Researcher Affiliation | Academia | 1ETH, Zürich, Switzerland 2EPFL, Switzerland. Correspondence to: Tian Guo <tian.guo@gess.eth.ch>. |
| Pseudocode | No | The paper does not contain any sections explicitly labeled as 'Pseudocode' or 'Algorithm', nor are there any structured code-like blocks detailing a procedure. |
| Open Source Code | No | The paper does not provide any explicit statements about releasing source code for the described methodology or links to a code repository. |
| Open Datasets | Yes | PLANT: This records the time series of energy production of a photo-voltaic power plant in Italy (Ceci et al., 2017).; SML is a public dataset used for indoor temperature forecasting. Same as (Qin et al., 2017), |
| Dataset Splits | Yes | PLANT: It provides 20842 sequences split into training (70%), validation (10%) and testing sets (20%).; SML: The first 3200, the following 400 and the last 537 data points are respectively used for training, validation, and test. |
| Hardware Specification | No | The paper does not provide specific hardware details such as GPU or CPU models, processor types, or memory amounts used for running the experiments. |
| Software Dependencies | No | The paper states 'We implemented IMV-LSTM and deep learning baselines with Tensorflow.' However, it does not provide specific version numbers for TensorFlow or any other software dependencies. |
| Experiment Setup | Yes | We used Adam with the mini-batch size 64 (Kingma & Ba, 2014). For the size of recurrent and dense layers in the baselines, we conduct grid search over {16, 32, 64, 128, 256, 512}. The size of IMV-LSTM layers is set by the number of neurons per variable selected from {10, 15, 20, 25}. Dropout is selected in {0, 0.2, 0.5}. Learning rate is searched in {0.0005, 0.001, 0.005, 0.01, 0.05}. L2 regularization is added with the coefficient chosen from {0.0001, 0.001, 0.01, 0.1, 1.0}. |