No abstract

Neural Architecture Search (NAS) has shown excellent results in designing architectures for computer vision problems. NAS alleviates the need for human-defined settings by automating architecture design and engineering. However, NAS methods tend to be slow, as they require large amounts of GPU computation. This bottleneck is mainly due to the performance estimation strategy, which requires the evaluation of the generated architectures, mainly by training them, to update the sampler method. In this paper, we propose EPE-NAS, an efficient performance estimation strategy, that mitigates the problem of evaluating networks, by scoring untrained networks and creating a correlation with their trained performance. We perform this process by looking at intra and inter-class correlations of an untrained network. We show that EPE-NAS can produce a robust correlation and that by incorporating it into a simple random sampling strategy, we are able to search for competitive networks, without requiring any training, in a matter of seconds using a single GPU. Moreover, EPE-NAS is agnostic to the search method, since it focuses on the evaluation of untrained networks, making it easy to integrate into almost any NAS method.

No abstract

A scheduling method in a robotic network cloud system with minimal makespan is beneficiary in the sense that the system can complete all of its assigned tasks in the fastest way. Robotic network cloud systems can be translated into graphs, with nodes representing hardware with independent computational processing power and edges as data transmissions between nodes. Tasks time windows constraints are a natural way of ordering the tasks. The makespan is the maximum time duration from the time that a node starts to perform its first scheduled task to the time that all the nodes complete their final scheduled tasks. The load balancing scheduling ensures that the time windows from the time that the first node completes its final scheduled tasks to the time that all the other nodes complete their final scheduled tasks are as narrow as possible. We propose a new load balancing algorithm for task scheduling such that the makespan is minimal. We prove the correctness of the proposed algorithm and present simulations illustrating the obtained results.

Ecology, biogeography and conservation biology, among other disciplines, often rely on species identity, distribution and abundance to perceive and explain patterns in space and time. Yet, species are not independent units in the way they interact with their environment. Species often perform similar roles in networks and their ecosystems, and at least partial redundancy or difference of roles might explain co-existence, competitive exclusion or other patterns reflected at the community level. Therefore, considering species traits, that is, the organisms’ functional properties that interact with the environment, might be of utmost importance in the study of species relative abundances. Several descriptive measures of diversity, such as the species-area relationship (SAR) and the species abundance distribution (SAD), have been used extensively to characterize the communities and as a possible window to gain insight into underlying processes shaping and maintaining biodiversity. However, if the role of species in a community is better assessed by their functional attributes, then one should also study the SAR and the SAD by using trait-based approaches, and not only taxonomic species. Here we merged species according to their similarity in a number of traits, creating functional units, and used these new units to study the equivalent patterns of the SAR and of the SAD (functional units abundance distributions - FUADs), with emphasis on their spatial scaling characteristics. This idea was tested using data on arthropods collected in Terceira island, in the Azorean archipelago. Our results showed that diversity scales differently depending on whether we use species or functional units. If what determines species communities’ dynamics is their functional diversity, then our results suggest that we may need to revaluate the commonly assumed patterns of species diversity and, concomitantly, the role of the underlying processes.