Recurrent Ladder Networks

Authors: Isabeau Prémont-Schwarz, Alexander Ilin, Tele Hao, Antti Rasmus, Rinu Boney, Harri Valpola

NeurIPS 2017 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental We demonstrate that the recurrent Ladder is able to handle a wide variety of complex learning tasks that benefit from iterative inference and temporal modeling. The architecture shows close-to-optimal results on temporal modeling of video data, competitive results on music modeling, and improved perceptual grouping based on higher order abstractions, such as stochastic textures and motion cues. We present results for fully supervised, semi-supervised, and unsupervised tasks. (from Abstract) and 3 Experiments with temporal data (Section 3 title).
Researcher Affiliation Industry Isabeau Prémont-Schwarz, Alexander Ilin, Tele Hotloo Hao, Antti Rasmus, Rinu Boney, Harri Valpola The Curious AI Company {isabeau,alexilin,hotloo,antti,rinu,harri}@cai.fi
Pseudocode No The paper describes the model's architecture and equations (1), (2), (3), and further details in Appendix A. However, it does not contain a clearly labeled 'Pseudocode' or 'Algorithm' block, nor structured steps formatted like code.
Open Source Code No The paper does not provide an explicit statement about releasing source code, nor does it include a link to a code repository.
Open Datasets Yes We use a dataset where we know how to do optimal inference in order to be able to compare the results of the RLadder to the optimal ones. To this end we designed the Occluded Moving MNIST dataset. It consists of MNIST digits... The digits are split into training, validation, and test sets according to the original MNIST split. (Section 3.1). Other datasets mentioned include midi dataset converted to piano rolls [6] and Brodatz dataset [7], and moving MNIST [25]. All are standard datasets or cited properly.
Dataset Splits Yes The digits are split into training, validation, and test sets according to the original MNIST split. (Section 3.1, Occluded Moving MNIST)
Hardware Specification No The paper does not provide specific hardware details (e.g., GPU/CPU models, memory amounts, or detailed computer specifications) used for running its experiments.
Software Dependencies No The paper mentions using 'LSTM [15] or GRU [8] cells' but does not specify any software dependencies with version numbers (e.g., Python, PyTorch, TensorFlow versions, or specific libraries with their versions).
Experiment Setup No The paper describes the training tasks and some architectural details, such as 'The RLadder is trained to predict the next occluded frame' (Section 3.1) and 'The number of groups was set to K = 3' (Section 4.2). However, specific hyperparameters like learning rates, batch sizes, number of epochs, or optimizer settings are not explicitly provided in the main text.