Effective Non-Random Extreme Learning Machine
This addresses the sensitivity and design issues in ELMs for regression, but it is incremental as it builds on the existing ELM framework with signal processing concepts.
The paper tackled the challenges of random weight initialization and architecture design in Extreme Learning Machines (ELMs) for regression by introducing the Effective Non-Random ELM (ENR-ELM), which eliminates randomness and simplifies design while maintaining comparable predictive performance on synthetic and real datasets.
The Extreme Learning Machine (ELM) is a growing statistical technique widely applied to regression problems. In essence, ELMs are single-layer neural networks where the hidden layer weights are randomly sampled from a specific distribution, while the output layer weights are learned from the data. Two of the key challenges with this approach are the architecture design, specifically determining the optimal number of neurons in the hidden layer, and the method's sensitivity to the random initialization of hidden layer weights. This paper introduces a new and enhanced learning algorithm for regression tasks, the Effective Non-Random ELM (ENR-ELM), which simplifies the architecture design and eliminates the need for random hidden layer weight selection. The proposed method incorporates concepts from signal processing, such as basis functions and projections, into the ELM framework. We introduce two versions of the ENR-ELM: the approximated ENR-ELM and the incremental ENR-ELM. Experimental results on both synthetic and real datasets demonstrate that our method overcomes the problems of traditional ELM while maintaining comparable predictive performance.