Band-Limited Gaussian Processes: The Sinc Kernel
Authors: Felipe Tobar
NeurIPS 2019 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | The developed theory is complemented with illustrative graphic examples and validated experimentally using real-world data. and Section 6 validates the proposed kernel through numerical experiments with real-world signals. |
| Researcher Affiliation | Academia | Felipe Tobar Center for Mathematical Modeling Universidad de Chile ftobar@dim.uchile.cl |
| Pseudocode | No | The paper does not contain structured pseudocode or algorithm blocks. |
| Open Source Code | No | The paper mentions 'the sinc function implemented in Python' but does not provide concrete access to source code for the methodology described in the paper. |
| Open Datasets | Yes | MIT-BIH database [7], TIMIT repository [6], Mauna Loa monthly CO2 concentration series |
| Dataset Splits | Yes | Using one third of the data, training the GP-sinc (plus noise variance) was achieved by maximum likelihood... and We focused on the reconstruction setting using only 200 (out of 1000) observations with added Gaussian noise... and used a subset of 1200 (out of 9000) observations samples... |
| 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 mentions 'the sinc function implemented in Python' but does not provide specific ancillary software details with version numbers. |
| Experiment Setup | Yes | Using one third of the data, training the GP-sinc (plus noise variance) was achieved by maximum likelihood, were both the BFGS [33] and Powell [20] optimisers yielded similar results. and with added Gaussian noise of standard deviation equal to a 10% of that of the audio signal. and using carrier of frequency 2Hz (most of the power of the heart-rate signals is contained below 1Hz), and used a subset of 1200 (out of 9000) observations samples with added noise of standard deviation equal to a 20% of that of the modulated signal. |