Recent advances in AutoML have led to automated tools that can compete with machine learning experts on supervised learning tasks. However, current AutoML tools do not yet support modern neural networks effectively. In this work, we present a first version of Auto-Net, which provides automatically-tuned feed-forward neural networks without any human intervention. We report results on datasets f...

The location of broken insulators in aerial images is a challenging task. This paper, focusing on the self-blast glass insulator, proposes a deep learning solution. We address the broken insulators location problem as a low signal-noise-ratio image location framework with two modules: 1) object detection based on Fast R-CNN, and 2) classification of pixels based on U-net. A diverse aerial image...

Extended Petri Nets have been applied to artificial intelligence reasoning processes, in areas such as planning, uncertainty reasoning, knowledgebased intelligent systems, and qualitative simulation. Creating Petri Net domain models faces the same challenges that confront all knowledge-intensive AI performance systems: model specification, knowledge acquisition, and refinement. Thus, a fundamen...

We descr ibe a l ea rn ing paradigm designed to improve the performance of a robot in a p a r t i a l l y unpred ic tab le environment. The paradigm was suggested by phenomena observed in animal behavior and it models aspects of t ha t behavior. (See Fl f o r d e t a i l s . ) An implementation as a working program is under way, intended f o r i nco rpo ra t i on in the now ope ra t i ona l JPL...

A bill presented by the Swedish Government in 2001 stated that higher education should aim for a broader recruitment of students. The use of ICT-tools is pointed out as a way of reaching new student groups, e.g. students who are immobile due to their social situation or physical handicap. At the same time, a number of regions in Sweden struggle with negative net migration that is to a large ext...

The use of supervised neural networks for the estimation of seismic source parameters from SAR interferometric data is presented in this paper. The RNGCHN software allowed the generation of the input-output pairs necessary for the learning phase of the net. After being trained, the net has been tested on real measured data. The obtained results encourage future developments of such an approach.

Road extraction from aerial images has been a hot research topic in the field of remote sensing image analysis. In this letter, a semantic segmentation neural network which combines the strengths of residual learning and U-Net is proposed for road area extraction. The network is built with residual units and has similar architecture to that of U-Net. The benefits of this model is two-fold: firs...

Cascade is a widely used approach that rejects obvious negative samples at early stages for learning better classifier and faster inference. This paper presents chained cascade network (CC-Net). In this CC-Net, the cascaded classifier at a stage is aided by the classification scores in previous stages. Feature chaining is further proposed so that the feature learning for the current cascade sta...

The energy spectrum of the atmospheric muon neutrino flux was measured with the IceCube detector in the 59-string configuration, using an unfolding procedure. This measurement extended IceCube’s reach for atmospheric neutrinos up to 1PeV in energy. This extension in energy was obtained by using a machine learning algorithm preceeded by a dedicated feature selection for event selection, and by a...

We give a description of a Petri net-based framework for modelling and analysing biochemical pathways, which unifies the qualitative, stochastic and continuous paradigms. Each perspective adds its contribution to the understanding of the system, thus the three approaches do not compete, but complement each other. We illustrate our approach by applying it to an extended model of the three stage ...