Neural Delay Differential Equations
Authors: Qunxi Zhu, Yao Guo, Wei Lin
ICLR 2021 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | More importantly, we use several illustrative examples to demonstrate the outstanding capacities of the NDDEs and the NDDEs with ODEs initial value. Specifically, (1) we successfully model the delayed dynamics where the trajectories in the lower-dimensional phase space could be mutually intersected... and (2) we achieve lower loss and higher accuracy not only for the data produced synthetically by complex models but also for the real-world image datasets, i.e., CIFAR10, MNIST, and SVHN. |
| Researcher Affiliation | Academia | Qunxi Zhu, Yao Guo & Wei Lin School of Mathematical Science, Research Institute of Intelligent Complex Systems and ISTBI State Key Laboratory of Medical Neurobiology and MOE Frontiers Center for Brain Science Fudan University Shanghai 200433, China {qxzhu16,yguo,wlin}@fudan.edu.cn |
| Pseudocode | Yes | Algorithm 1 Piece-wise reverse-mode derivative of an DDE initial function problem |
| Open Source Code | No | The paper does not provide any explicit statement or link for open-source code. |
| Open Datasets | Yes | we achieve lower loss and higher accuracy not only for the data produced synthetically by complex models but also for the real-world image datasets, i.e., CIFAR10, MNIST, and SVHN. |
| Dataset Splits | Yes | We split the trajectories into two parts. The first part within the time interval [0, 3] is used as the training data. The other part is used for testing. ... The training processes on MNIST, CIFAR10, and SVHN are shown in Fig. 8. |
| Hardware Specification | No | The paper does not provide specific hardware details (e.g., CPU/GPU models, memory) used for running experiments. |
| Software Dependencies | No | For each model, we choose the optimizer Adam with 1e-3 as the learning rate, 64 as the batch size, and 5 as the number of the training epochs. ... The paper does not specify software versions for any libraries or tools used. |
| Experiment Setup | Yes | For each model, we choose the optimizer Adam with 1e-3 as the learning rate, 64 as the batch size, and 5 as the number of the training epochs. ... we choose the optimizer Adam through 1e-3 as the learning rate, 256 as the batch size, and 30 as the number of the training epochs. |