LiteLSTM Architecture for Deep Recurrent Neural Networks
This addresses efficiency for big data applications like IoT security and medical data, though it appears incremental as a modification of LSTM.
The paper tackles the high computational cost of LSTM networks by proposing a LiteLSTM architecture that reduces components through weight sharing, achieving maintained performance on datasets from computer vision and cybersecurity.
Long short-term memory (LSTM) is a robust recurrent neural network architecture for learning spatiotemporal sequential data. However, it requires significant computational power for learning and implementing from both software and hardware aspects. This paper proposes a novel LiteLSTM architecture based on reducing the computation components of the LSTM using the weights sharing concept to reduce the overall architecture cost and maintain the architecture performance. The proposed LiteLSTM can be significant for learning big data where time-consumption is crucial such as the security of IoT devices and medical data. Moreover, it helps to reduce the CO2 footprint. The proposed model was evaluated and tested empirically on two different datasets from computer vision and cybersecurity domains.