Deep Learning with the Random Neural Network and its Applications
This work addresses the problem of improving computational efficiency in deep learning for researchers and practitioners, though it appears incremental as it builds on prior RNN investigations.
The paper tackles the challenge of bridging deep learning with the random neural network (RNN), a spiking network model, and demonstrates that RNN-based deep learning tools are faster and more energy-efficient than existing methods.
The random neural network (RNN) is a mathematical model for an "integrate and fire" spiking network that closely resembles the stochastic behaviour of neurons in mammalian brains. Since its proposal in 1989, there have been numerous investigations into the RNN's applications and learning algorithms. Deep learning (DL) has achieved great success in machine learning. Recently, the properties of the RNN for DL have been investigated, in order to combine their power. Recent results demonstrate that the gap between RNNs and DL can be bridged and the DL tools based on the RNN are faster and can potentially be used with less energy expenditure than existing methods.