Adaptive Neural Trees

Authors: Ryutaro Tanno, Kai Arulkumaran, Daniel Alexander, Antonio Criminisi, Aditya Nori

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

Reproducibility Variable Result LLM Response
Research Type Experimental We empirically validate these benefits for regression and classification through experiments on the SARCOS (Vijayakumar & Schaal, 2000), MNIST (Le Cun et al., 1998) and CIFAR-10 (Krizhevsky & Hinton, 2009) datasets.
Researcher Affiliation Collaboration 1University College London, UK 2Imperial College London, UK 3Microsoft Research, Cambridge, UK.
Pseudocode Yes We include a pseudocode of the training algorithm in Supp. Sec. A.
Open Source Code Yes Codes: https://github.com/rtanno21609/Adaptive Neural Trees
Open Datasets Yes We evaluate ANTs using the SARCOS multivariate regression dataset (Vijayakumar & Schaal, 2000), and the MNIST (Le Cun et al., 1998) and CIFAR-10 (Krizhevsky & Hinton, 2009) classification datasets.
Dataset Splits Yes The best model is picked based on the performance on the same validation set of 5k examples as before.
Hardware Specification No Full training details, including training times on a single GPU, are provided in Supp. Sec. C and D.
Software Dependencies No All of our models are implemented in Py Torch (Paszke et al., 2017)1.
Experiment Setup No Full training details, including training times on a single GPU, are provided in Supp. Sec. C and D.