@article{Santurkar:2019,
    title = {How Does Batch Normalization Help Optimization?},
    author = {Shibani Santurkar and Dimitris Tsipras and Andrew Ilyas and
        Aleksander Madry},
    year = {2019},
    note = {arXiv pre-print},
    url = {https://arxiv.org/abs/1805.11604}
}

@article{Chen:2021,
    author = {Chen, Leiyu and Li, Shaobo and Bai, Qiang and Yang, Jing and
        Jiang, Sanlong and Miao, Yanming},
    title = {Review of Image Classification Algorithms Based on Convolutional
        Neural Networks},
    journal = {Remote Sensing},
    volume = {13},
    year = {2021},
    number = {22},
    url = {https://doi.org/10.3390/rs13224712},
}

@inproceedings{Nilsback:2008,
    author = {Maria-Elena Nilsback and Andrew Zisserman},
    title = {Automated Flower Classification over a Large Number of Classes},
    booktitle = {Indian Conference on Computer Vision, Graphics and Image
        Processing},
    year = {2008},
}


@inproceedings{Varma:2007,
    author = {Varma, Manik and Ray, Debajyoti},
    booktitle = {IEEE 11th International Conference on Computer Vision},
    publisher = {IEEE},
    title = {Learning The Discriminative Power-Invariance Trade-Off},
    year = {2007},
    pages = {1--8},
    url = {https://doi.org/10.1109/ICCV.2007.4408875}
}


@inproceedings{Xia:2017,
    author = {Xiaoling Xia and Cui Xu and Bing Nan},
    booktitle = {2017 2nd International Conference on Image, Vision and
        Computing (ICIVC)},
    publisher = {IEEE},
    title = {Inception-v3 for flower classification},
    year = {2017},
    pages = {783--787},
    url = {https://doi.org/10.1109/ICIVC.2017.7984661}
}

@article{Ioffe:2015,
    title = {Batch Normalization: Accelerating Deep Network Training by
        Reducing Internal Covariate Shift},
    author = {Sergey Ioffe and Christian Szegedy},
    year = {2015},
    note = {arXiv pre-print},
    url = {https://arxiv.org/abs/1502.03167}
}

@inproceedings{Wang:2016,
    author = {Wang, Jichen and Lin, Jun and Wang, Zhongfeng},
    booktitle = {2016 8th International Conference on Wireless Communications \&
        Signal Processing (WCSP)},
    title = {Efficient convolution architectures for convolutional neural
        network},
    year = {2016},
    publisher = {IEEE},
    pages = {1--5},
    url = {https://doi.org/10.1109/WCSP.2016.7752726}
}

@article{Luo:2019,
    title = {Towards Understanding Regularization in Batch Normalization},
    author = {Ping Luo and Xinjiang Wang and Wenqi Shao and Zhanglin Peng},
    year = {2019},
    note = {arXiv pre-print},
    url = {http://arxiv.org/abs/1809.00846}
}

@article{Laarhoven:2017,
    title = {$L_2$ Regularization versus Batch and Weight Normalization},
    author = {Twan van Laarhoven},
    year = {2017},
    note = {arXiv pre-print},
    url = {https://arxiv.org/abs/1706.05350}
}

@article{Hahnloser:2000,
    title = {Digital selection and analogue amplification coexist in a
        cortex-inspired silicon circuit},
    author = {Richard H. R. Hahnloser and Rahul Sarpeshkar and Misha A. Mahowald
        and Rodney J. Douglas and H. Sebastian Seung},
    year = {2000},
    pages = {947--951},
    journal = {Nature},
    volume = {405}
}

@article{Agarap:2019,
    title = {Deep Learning using Rectified Linear Units (ReLU)},
    author = {Abien Fred Agarap},
    year = {2019},
    url = {https://arxiv.org/abs/1803.08375},
    note = {arXiv pre-print}
}

@inproceedings{Nagi:2011,
    author = {Nagi, Jawad and Ducatelle, Frederick and Di Caro, Gianni A. and
        Cireşan, Dan and Meier, Ueli and Giusti, Alessandro and Nagi, Farrukh
        and Schmidhuber, Jürgen and Gambardella, Luca Maria},
    booktitle = {2011 IEEE International Conference on Signal and Image
        Processing Applications (ICSIPA)},
    title = {Max-pooling convolutional neural networks for vision-based hand
    gesture recognition},
    year = {2011},
    pages = {342--347},
    url = {https://doi.org/10.1109/ICSIPA.2011.6144164}
}

@article{Sun:2017,
    title = {Learning Pooling for Convolutional Neural Network},
    journal = {Neurocomputing},
    volume = {224},
    pages = {96-104},
    year = {2017},
    issn = {0925-2312},
    url = {https://doi.org/10.1016/j.neucom.2016.10.049},
    author = {Manli Sun and Zhanjie Song and Xiaoheng Jiang and Jing Pan and
        Yanwei Pang}
}

@inproceedings{Jie:2018,
    author = {Cao, Jie and Su, Zhe and Yu, Liyun and Chang, Dongliang and Li,
        Xiaoxu and Ma, Zhanyu},
    booktitle = {2018 Chinese Automation Congress (CAC)},
    title = {Softmax Cross Entropy Loss with Unbiased Decision Boundary for Image
        Classification},
    year = {2018},
    pages = {2028--2032},
    url = {https://doi.org/10.1109/CAC.2018.8623242}
}

@inproceedings{Konar:2020,
    author = {Konar, Jinia and Khandelwal, Prerit and Tripathi, Rishabh},
    booktitle = {2020 IEEE International Students' Conference on
        Electrical,Electronics and Computer Science (SCEECS)},
    title = {Comparison of Various Learning Rate Scheduling Techniques on
        Convolutional Neural Network},
    year = {2020},
    pages = {1--5},
    url = {http://doi.org/10.1109/SCEECS48394.2020.94}
}

@article{Loshchilov:2017,
    title = {{SGDR}: Stochastic Gradient Descent with Warm Restarts},
    author = {Ilya Loshchilov and Frank Hutter},
    year = {2017},
    url = {https://arxiv.org/abs/1608.03983},
    note = {arXiv pre-print},
}

@article{Kandel:2020,
    title = {The effect of batch size on the generalizability of the
        convolutional neural networks on a histopathology dataset},
    journal = {ICT Express},
    volume = {6},
    number = {4},
    pages = {312-315},
    year = {2020},
    issn = {2405-9595},
    url = {https://www.sciencedirect.com/science/article/pii/S2405959519303455},
    author = {Ibrahem Kandel and Mauro Castelli},
}

@article{Hardt:2016,
    title = {Train faster, generalize better: Stability of stochastic gradient
        descent},
    author = {Moritz Hardt and Benjamin Recht and Yoram Singer},
    year = {2016},
    url = {https://arxiv.org/abs/1509.01240},
    note = {arXiv pre-print}
}