Affiliation:
1. Vellore Institute of Technology, India
2. Andhra University, India
Abstract
Lightweight deep learning is a subfield of artificial intelligence and machine learning that prioritises efficiency and compactness while developing deep learning models. It is ideal for low-powered mobile phones, embedded systems, and internet-of-things devices due to their speed and low latency. To make lightweight deep learning models, pruning and quantization are used to remove unnecessary parameters and reduce model weight accuracy. Transfer learning is used to fine-tune a pre-trained deep learning model on a smaller dataset. This chapter introduces the fundamentals of lightweight deep learning, including various lightweight models and their applications across different industries.
Reference30 articles.
1. Arora, S., Dalmia, S., Denisov, P., Chang, X., Ueda, Y., Peng, Y., & Watanabe, S. (2022, May). Espnet-slu: Advancing spoken language understanding through espnet. In ICASSP 2022-2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) (pp. 7167-7171). IEEE.
2. 2021, December). A study of transducer based end-to-end ASR with ESPnet: Architecture, auxiliary loss and decoding strategies.;F.Boyer;2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)
3. Tarigan, Y. F., Gunawan, T. S., & Hayadi, B. H. (2023, March). Combination Of SqueezeNet And Multilayer Backpropagation Algorithm In Hanacaraka Script Recognition. In International Conference on Information Science and Technology Innovation (ICoSTEC) (Vol. 2, pp. 163-170). IEEE.
4. DRDA-Net: Dense residual dual-shuffle attention network for breast cancer classification using histopathological images
5. SqueezeNet for the forecasting of the energy demand using a combined version of the sewing training-based optimization algorithm
Cited by
1 articles.
订阅此论文施引文献
订阅此论文施引文献，注册后可以免费订阅5篇论文的施引文献，订阅后可以查看论文全部施引文献