The Functional Neural Process

Authors: Christos Louizos, Xiahan Shi, Klamer Schutte, Max Welling

NeurIPS 2019 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental We experimentally evaluate FNPs on the tasks of toy regression and image classification and show that, when compared to baselines that employ global latent parameters, they offer both competitive predictions as well as more robust uncertainty estimates.
Researcher Affiliation Collaboration Christos Louizos University of Amsterdam TNO Intelligent Imaging c.louizos@uva.nl Xiahan Shi Bosch Center for Artificial Intelligence Uv A-Bosch Delta Lab xiahan.shi@de.bosch.com Klamer Schutte TNO Intelligent Imaging klamer.schutter@tno.nl Max Welling University of Amsterdam Qualcomm m.welling@uva.nl
Pseudocode No The paper does not contain structured pseudocode or algorithm blocks.
Open Source Code Yes We have open sourced an implementation of FNPs for both classification and regression along with example usages at https://github.com/AMLab-Amsterdam/FNP.
Open Datasets Yes We experimentally evaluate FNPs on the tasks of toy regression and image classification and show that, when compared to baselines that employ global latent parameters, they offer both competitive predictions as well as more robust uncertainty estimates.
Dataset Splits No The paper mentions training on datasets like MNIST and CIFAR-10 and using specific numbers of points for the reference set R and context points during training, but it does not provide explicit details about validation splits (e.g., percentages, sample counts, or specific methods for creating a distinct validation set).
Hardware Specification No The paper discusses training models and architectures but does not provide specific hardware details such as GPU models, CPU types, or memory specifications used for running the experiments.
Software Dependencies No The paper does not provide specific software dependencies with version numbers (e.g., Python version, PyTorch/TensorFlow version, CUDA version, or specific library versions).
Experiment Setup Yes For MNIST we used a Le Net-5 architecture that had two convolutional and two fully connected layers, whereas for CIFAR we used a VGG-like architecture that had 6 convolutional and two fully connected. In both experiments we used 300 random points from D as R for the FNPs and for NPs, in order to be comparable, we randomly selected up to 300 points from the current batch for the context points during training and used the same 300 points as FNPs for evaluation. The dimensionality of u, z was 32, 64 for the FNP models in both datasets, whereas for the NP the dimensionality of the global variable was 32 for MNIST and 64 for CIFAR.