An Architecture for Deep, Hierarchical Generative Models

Authors: Philip Bachman

NeurIPS 2016 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Experiments show that our approach achieves state-of-the-art performance on standard image modelling benchmarks, can expose latent class structure in the absence of label information, and can provide convincing imputations of occluded regions in natural images.
Researcher Affiliation Industry Philip Bachman phil.bachman@maluuba.com Maluuba Research
Pseudocode No The paper describes procedures in text, but does not contain structured pseudocode or algorithm blocks (clearly labeled algorithm sections or code-like formatted procedures).
Open Source Code Yes Exhaustive descriptions of the modules can be found in our code at: https://github.com/Philip-Bachman/Mat Nets-NIPS.
Open Datasets Yes We measured quantitative performance of Mat Nets on three datasets: MNIST, Omniglot [13], and CIFAR 10 [12]. We used the 28x28 version of Omniglot described in [2], which can be found at: https://github.com/yburda/iwae.
Dataset Splits No The paper does not provide specific dataset split information (exact percentages, sample counts, citations to predefined splits, or detailed splitting methodology) for a validation set.
Hardware Specification No The paper does not provide specific hardware details (exact GPU/CPU models, processor types with speeds, memory amounts, or detailed computer specifications) used for running its experiments.
Software Dependencies No The paper does not provide specific ancillary software details (e.g., library or solver names with version numbers) needed to replicate the experiment.
Experiment Setup No The paper states, "Complete hyperparameters for model architecture and optimization can be found in the code at https://github.com/Philip-Bachman/Mat Nets-NIPS.", but does not provide specific experimental setup details (concrete hyperparameter values, training configurations, or system-level settings) directly in the main text.