On the Depth of Deep Neural Networks: A Theoretical View

Authors: Shizhao Sun, Wei Chen, Liwei Wang, Xiaoguang Liu, Tie-Yan Liu

AAAI 2016 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Our experiments show that in this way, we achieve significantly better test performance. We have conducted extensive experiments on benchmark datasets to test the performance of LMDNN.
Researcher Affiliation Collaboration Shizhao Sun,1, Wei Chen,2 Liwei Wang,3 Xiaoguang Liu,1 and Tie-Yan Liu2 1College of Computer and Control Engineering, Nankai University, Tianjin, 300071, P. R. China 2Microsoft Research, Beijing, 100080, P. R. China 3Key Laboratory of Machine Perception (MOE), School of EECS, Peking University, Beijing, 100871, P. R. China
Pseudocode No The paper does not contain structured 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 conducted experiments on two datasets, MNIST (Le Cun et al. 1998) and CIFAR-10 (Krizhevsky 2009).
Dataset Splits No The paper mentions tuning hyperparameters on a 'validation set' but does not provide specific dataset split information (e.g., percentages, sample counts, or predefined splits) for training, validation, or testing.
Hardware Specification No The paper does not provide specific hardware details (e.g., GPU/CPU models, memory, or detailed computer specifications) used for running its experiments.
Software Dependencies No The paper mentions 'Caffe (Jia et al. 2014)' but does not provide specific version numbers for software dependencies.
Experiment Setup No The paper mentions using 'well-tuned network structures' and tuning a 'margin penalty coefficient λ' and that 'Each model was trained for 10 times with different initializations', but it does not provide concrete hyperparameter values or detailed training configurations (e.g., learning rate, batch size, optimal λ values) in the main text for reproduction.