Conditional Neural Processes

Authors: Marta Garnelo, Dan Rosenbaum, Christopher Maddison, Tiago Ramalho, David Saxton, Murray Shanahan, Yee Whye Teh, Danilo Rezende, S. M. Ali Eslami

ICML 2018 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental 4. Experimental Results
Researcher Affiliation Collaboration 1Deep Mind, London, UK 2Imperial College London, London, UK.
Pseudocode No The paper does not include any pseudocode or algorithm blocks.
Open Source Code No The paper does not provide concrete access to source code for the methodology described.
Open Datasets Yes We test CNP on two different data sets: the MNIST handwritten digit database (Le Cun et al., 1998) and large-scale Celeb Faces Attributes (Celeb A) dataset (Liu et al., 2015). and Finally, we apply the model to one-shot classification using the Omniglot dataset (Lake et al., 2015)
Dataset Splits No The paper mentions using 1,200 randomly selected classes as a training set and the remainder as a testing dataset for Omniglot, but it does not specify explicit training/validation/test splits with percentages or counts for any of the datasets used.
Hardware Specification No The paper does not provide specific hardware details (e.g., GPU/CPU models, memory) used for running its experiments.
Software Dependencies No The paper mentions using the Adam optimizer but does not provide specific version numbers for any software dependencies (e.g., deep learning frameworks, libraries).
Experiment Setup Yes The observed points are encoded using a three layer MLP encoder h with a 128 dimensional output representation ri. The representations are aggregated into a single representation r = 1 n P ri which is concatenated to xt and passed to a decoder g consisting of a five layer MLP. The decoder outputs a Gaussian mean and variance for the target outputs ˆyt. We train the model to maximize the log-likelihood of the target points using the Adam optimizer (Kingma & Ba, 2014).