A method for creating a non–linear encoder–decoder for multidimensional data with compact representations is presented. The commonly used technique of autoassociation is extended to allow non–linear representations, and an objective function which penalizes activations of individual hidden units is shown to result in minimum dimensional encodings with respect to allowable error in reconstruction.

According to the Formal Theory of Creativity (1990-2010), a creative agent – one that never stops generating non-trivial, novel, and surprising behaviours and data – must have two learning components: a general reward optimiser or reinforcement learner, and an adaptive encoder of the agent’s growing data history (the record of the agent’s interaction with its environment). The learning progress...

Existing analyses of ‘zooming’ quantisation schemes for bit-rate-limited control systems rely on the encoder and controller being initialised with identical internal states. Due to the quantiser discontinuity and the plant instability, it was not clear if closed-loop stability was possible if the encoder and controller commenced from different initial conditions. In this article, we consider pa...

Encoder-decoder networks are popular for modeling sequences probabilistically in many applications. These models use the power of the Long Short-Term Memory (LSTM) architecture to capture the full dependence among variables, unlike earlier models like CRFs that typically assumed conditional independence among non-adjacent variables. However in practice encoder-decoder models exhibit a bias towa...

Main challenges in future video prediction are high variability in videos, temporal propagation of errors, and non-specificity of future frames. This work introduces bijective Gated Recurrent Units (bGRU). Standard GRUs update a state, exposed as output, given an input. We extend them by considering the input as another recurrent state, and update it given the output using an extra set of logic...

This article presents a self-calibration procedure and the experimental results for the geometrical characterisation of a 2D laser system operating along a large working range (50 mm × 50 mm) with submicrometre uncertainty. Its purpose is to correct the geometric errors of the 2D laser system setup generated when positioning the two laser heads and the plane mirrors used as reflectors. The non-...

The results of a transmission experiment of MPEG-2 coded video data over a satellite link affected by noise are presented. The goal was to investigate under which conditions this type of transmission is economically feasible. The scalability feature of the MPEG-2 encoder was used to produce different bitstreams of the same video sequence. We wanted to verify the best combinations among video an...

Background Cardiovascular disease poses a great financial risk on households in countries without universal health coverage like Ethiopia. This paper aims to estimate the magnitude and intensity of catastrophic health expenditure and factors associated with catastrophic health expenditure for prevention and treatment of cardiovascular disease in general and specialised cardiac hospitals in Addi...