On Fast Dropout and its Applicability to Recurrent Networks
Authors: Unknown
ICLR 2014 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | We positively test the hypothesis that this improves the performance of RNNs on four musical data sets. and 3 Experiments and Results |
| Researcher Affiliation | Collaboration | Justin Bayer, Christian Osendorfer, Daniela Korhammer, Nutan Chen, Sebastian Urban and Patrick van der Smagt Lehrstuhl f ur Robotik und Echtzeitsysteme Fakult at f ur Informatik Technische Universit at M unchen bayer.justin@googlemail.com, osendorf@in.tum.de, korhammd@in.tum.de, ntchen86@gmail.com, surban@tum.de, smagt@brml.org |
| Pseudocode | No | The paper does not contain any structured pseudocode or algorithm blocks. |
| Open Source Code | No | The paper does not provide any concrete access to source code for the described methodology. |
| Open Datasets | Yes | The data consists of four distinct data sets, namely Piano-midi.de (classical piano music), Nottingham (folk music), Muse Data (orchestral) and JSBChorales (chorales by Johann Sebastian Bach). and using the same split as in (Bengio et al., 2012). |
| Dataset Splits | Yes | We report the test loss of the model with the lowest validation error over all training runs, using the same split as in (Bengio et al., 2012). and splitting all sequences of the training and validation set into chunks of length of 100. |
| Hardware Specification | No | The paper does not provide specific hardware details (e.g., exact GPU/CPU models, processor types, or memory amounts) used for running its experiments. |
| Software Dependencies | No | The paper mentions software like Theano and Python for SciPy but does not provide specific version numbers for these or other key software components. |
| Experiment Setup | Yes | All experiments were done by performing a random search (Bergstra and Bengio, 2012) over the hyper parameters (see Table 2 in the Appendix for an overview)... and Table 2: Hyper parameter ranges and parameter distributions for the musical data sets. and Table 3: Hyper parameters used for the musical data experiments. |