Abstract
In artificial intelligence, the area is going rapidly towards tackling and solving problems that are intellectually challenging for human beings, its almost straightforward for machines. A list of formal and analytical rules creates the problem. The computer gains experience automatically by executing the same problem again and again by repeating the ideas by defining the relationship between the concepts. There are many architectures to enhance the system to perform accurately and efficiently. The architecture helps to classify and extract the multiple unique features using many stages from the source data. This innovative CNN architecture reduces the complex problem by breaking into simple concepts, and then it is fed into hidden layers of the architecture. Further, it concentrates on loss function, structural reformulation, optimization, weight sharing, parameter regularization and generalization. Thus, the computer learns more complexity about the concepts on its own, and it works more accurately and efficiently.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Suchy R, Ezekiel S, Cornacchia M (2017) Fusion of deep convolutional neural networks. In: 2017 IEEE applied imagery pattern recognition workshop (AIPR). IEEE
Khan A et al. A survey of the recent architectures of deep convolutional neural networks. arXiv: arXiv:1901.06032
Kůrková V et al (eds) (2018) Artificial neural networks and machine learning–ICANN 2018: 27th International conference on artificial neural networks, Rhodes, Greece, October 4–7, 2018, Proceedings, vol 11141. Springer
Gulshan V et al (2016) Development and validation of a deep learning algorithm for detection of diabetic retinopathy in retinal fundus photographs. Jama 316(22):2402–2410
Yamashita R et al (2018) Convolutional neural networks: an overview and application in radiology. Insights Into Imaging 9(4):611–629
Ramachandran P, Barret Z, Le QV (2017) Searching for activation functions. arXiv: arXiv:1710.05941
Nair V, Hinton GE (2010) Rectified linear units improve restricted Boltzmann machines. In: Proceedings of the 27th international conference on machine learning (ICML-10)
Krizhevsky A, Sutskever I, Hinton GE (2012) Imagenet classification with deep convolutional neural networks. In: Advances in neural information processing systems
Dubey AK, Jain V (2019) Comparative study of convolution neural network’s Relu and Leaky-Relu activation functions. In: Applications of computing, automation, and wireless systems in electrical engineering. Springer, Singapore, pp 873–880
https://medium.com/@cdabakoglu/what-is-convolutional-neural-network-cnn-with-keras-cab447ad204c
Srivastava N et al (2014) Dropout: a simple way to prevent neural networks from overfitting. The J Mach Learn Res 15(1):1929–1958
Le Cun Y et al (1990) Handwritten digit recognition: applications of neural net chips and automatic learning. In: Neurocomputing. Springer, Berlin, Heidelberg, pp 303–318
Russakovsky O et al (2015) Imagenet large scale visual recognition challenge. Int J Comput Vis 115(3):211–252
Véstias MP (2019) A survey of convolutional neural networks on edge with reconfigurable computing. Algorithms 12(8):154
Goodfellow T, Bengio Y, Courville A (2017) Deep learning. Nat Methods 13(35)
https://medium.com/@smallfishbigsea/a-walk-through-of-alexnet-6cbd137a5637
He K et al (2016) Deep residual learning for image recognition. In: Proceedings of the IEEE conference on computer vision and pattern recognition
Karpathy A, Fei-Fei L (2015) Deep visual-semantic alignments for generating image descriptions. In: Proceedings of the IEEE conference on computer vision and pattern recognition
Simonyan K, Zisserman A (2014) Very deep convolutional networks for large-scale image recognition. arXiv: arXiv:1409.1556
Zeiler MD, Fergus R (2014) Visualizing and understanding convolutional networks. In: European conference on computer vision. Springer, Cham
https://leonardoaraujosantos.gitbooks.io/artificial-inteligence/content/googlenet.html
Erhan D et al (2009) Visualizing higher-layer features of a deep network. University of Montreal 1341(3):1
Jaderberg M, Simonyan K, Zisserman A (2015) Spatial transformer networks. In: Advances in neural information processing systems
https://mc.ai/cnn-architectures-lenet-alexnet-vgg-googlenet-and-resnet/
Huang FJ, Boureau Y-L, LeCun Y, Ranzato MA (2007) Unsupervised learning of invariant feature hierarchies with applications to object recognition. In: IEEE Conference on computer vision and pattern recognition CVPR’07, pp 1–8
https://towardsdatascience.com/residual-blocks-building-blocks-of-resnet-fd90ca15d6ec
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 Springer Nature Singapore Pte Ltd.
About this chapter
Cite this chapter
Bhargavi, G., Vaijayanthi, S., Arunnehru, J., Reddy, P.R.D. (2021). A Survey on Recent Deep Learning Architectures. In: Manoharan, K.G., Nehru, J.A., Balasubramanian, S. (eds) Artificial Intelligence and IoT. Studies in Big Data, vol 85. Springer, Singapore. https://doi.org/10.1007/978-981-33-6400-4_5
Download citation
DOI: https://doi.org/10.1007/978-981-33-6400-4_5
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-33-6399-1
Online ISBN: 978-981-33-6400-4
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)