This paper proposes a new structure of wavelet extreme learning machine i.e. an adaptive wavelet extreme learning machine (AW-ELM) for finger motion recognition using only two EMG channels. The adaptation mechanism is performed by adjusting the wavelet shape based on the input information. The performance of the proposed method is compared to ELM using wavelet (W-ELM0 and sigmoid (Sig-ELM) acti...

The optical domain is a promising field for the physical implementation of neural networks, due to speed and parallelism optics. Extreme learning machines (ELMs) are feed-forward networks in which only output weights trained, while internal connections randomly selected left untrained. Here we report on photonic ELM based frequency-multiplexed fiber setup. Multiplication by can be performed eit...

Extreme learning machine (ELM) has been proved to be an effective pattern classification and regression mechanism by researchers. However, its good performance is based on a large number of hidden layer nodes. With the increase nodes in layers, computation cost greatly increased. In this paper, we propose novel algorithm, named constrained voting extreme (CV-ELM). Compared with traditional ELM,...

Generalized Extreme Learning Machine (GELM) is a kind of fast and efficient learning algorithm for training Generalized Single-layer hidden Feedforward Networks (GSLFNs) acting on some metric spaces. However, noisy data often produce over-fitting phenomena in practical applications. Therefore, an improved learning algorithm, called Regularized Generalized Extreme Learning Machine (R-GELM), is p...