Emmanuel N. Osegi

  • Citations Per Year
Learn More
In this paper we present a modified version of the Hyperbolic Tangent Activation Function as a learning unit generator for neural networks. The function uses an integer calibration constant as an approximation to the Euler number, e, based on a quadratic Real Number Formula (RNF) algorithm and an adaptive normalization constraint on the input activations to(More)
A modified version of the Dijkstra algorithm using an inventive contraction hierarchy is proposed. The algorithm considers a directed acyclic graph with a conical or semi-circular structure for which a pair of edges is chosen iteratively from multi-sources. The algorithm obtains minimum paths by using a comparison process. The comparison process follows a(More)
HTM-MAT is a MATLAB® based toolbox for implementing cortical learning algorithms (CLA) including related cortical-like algorithms that possesses spatiotemporal properties. CLA is a suite of predictive machine learning algorithms developed by Numenta Inc. and is based on the hierarchical temporal memory (HTM). This paper presents an implementation of HTM-MAT(More)
 Abstract—In this paper, a framework is developed for power transformer (Generator Step up Unit) insulation life evaluation (PTILE) study on power system Network. Parameters used for studies include real time sample data obtained from power transformer field studies in the South-South Niger Delta region of Nigeria. It is used for performing simulations(More)
In the era of deep learning several unsupervised models have been developed to capture the key features in unlabeled handwritten data. Popular among them is the Restricted Boltzmann Machines (RBM). However, due to the novelty in handwritten multi-dialect data, the RBM may fail to generate an efficient representation. In this paper we propose a generative(More)
  • 1