The XIA-MAN architecture for intelligent humanoid robot control is proposed, a novel design in which perception and action are achieved via a combination of GA-evolved neural-net modules with existing open-source software packages; and cognition is achieved via the OpenCog Prime framework. XML is used to communicate between components, enabling simple pluggability of additional or modified comp...

We introduce a new neural architecture to learn the conditional probability of an output sequence with elements that are discrete tokens corresponding to positions in an input sequence. Such problems cannot be trivially addressed by existent approaches such as sequence-to-sequence [1] and Neural Turing Machines [2], because the number of target classes in each step of the output depends on the ...

Neural architecture search (NAS) has emerged as a promising avenue for automatically designing task-specific neural networks. Existing NAS approaches require one complete each deployment specification of hardware or objective. This is computationally impractical endeavor given the potentially large number application scenarios. In this paper, we propose Architecture Transfer (NAT) to overcome l...

Kohonen self-organizing feature maps are unsupervised learning neural networks that categorize or classify data. Efficient hardware implementation of such neural networks requires the definition of a certain number of simplifications to the original algorithm. In particular, multiplications should be avoided by means of simplifications in the distance metric, the neighborhood function and the l...

The excellent performance of deep neural networks has enabled us to solve several automatization problems, opening an era of autonomous devices. However, current deep net architectures are heavy with millions of parameters and require billions of floating point operations. Several works have been developed to compress a pre-trained deep network to reduce memory footprint and, possibly, computat...

{We consider neural units whose response functions are Lorentzians rather than the usual sigmoids or steps. This consideration is justiied by the fact that neurons can be paired and that a suitable diierence of the sigmoids of the paired neurons can create a window response function. Lorentzians are special cases of such windows and we take advantage of their simplicity to generate polynomial e...

This paper presents experimental results of an original approach to the Neural Network learning architecture for the control and the adaptive control of mobile robots. The basic idea is to use non-recurrent multi-layer-network and the backpropagation algorithm without desired outputs, but with a quadratic criterion which spezify the control objective. To illustrate this method, we consider an e...

We explore the applicability of deep convolutional neural networks (CNNs) for multiple landmark localization in medical image data. Exploiting the idea of regressing heatmaps for individual landmark locations, we investigate several fully convolutional 2D and 3D CNN architectures by training them in an end-to-end manner. We further propose a novel SpatialConfiguration-Net architecture that effe...

We propose a constructive method, inspired by Simpson’s Min-Max technique, for obtaining fuzzy neural networks. It adopts a cost function depending on a unique net parameter. This feature allows us to apply a simple unimodal search for determining this parameter and hence the architecture of the optimal net. The algorithm shows a good behavior with respect to other methods when applied to real ...