1 code implementation • 30 Sep 2022 • Aitor Martinez Seras, Javier Del Ser, Jesus L. Lobo, Pablo Garcia-Bringas, Nikola Kasabov
Specifically, this work presents a novel OoD detector that can identify whether test examples input to a Spiking Neural Network belong to the distribution of the data over which it was trained.
Out-of-Distribution Detection Out of Distribution (OOD) Detection
no code implementations • 23 Jul 2019 • Jesus L. Lobo, Javier Del Ser, Albert Bifet, Nikola Kasabov
Specially in these non-stationary scenarios, there is a pressing need for new algorithms that adapt to these changes as fast as possible, while maintaining good performance scores.
no code implementations • 3 Jun 2016 • Enmei Tu, Yaqian Zhang, Lin Zhu, Jie Yang, Nikola Kasabov
In this paper, we propose a new graph-based $k$NN algorithm which can effectively handle both Gaussian distributed data and nonlinear manifold distributed data.
no code implementations • 17 Mar 2016 • Enmei Tu, Nikola Kasabov, Jie Yang
This paper proposes a new method for an optimized mapping of temporal variables, describing a temporal stream data, into the recently proposed NeuCube spiking neural network architecture.