This paper describes MAKE-NMTViz, a project designed to help translators visualize neural machine translation outputs using explainable artificial intelligence visualization tools initially developed for computer vision.

This paper describes work in progress on Visualisation tools to foster collaborations between translators and computational scientists. We aim to describe how visualisation features can be used to explain translation and NMT outputs. We tested several visualisation functionalities with three NMT models based on Chinese-English, Spanish-English and French-English language pairs. We created three demos containing different visualisation tools and analysed them within the framework of performance-explainability, focusing on the translator’s perspective.

Wireless communications, including satellite communications, rely on the electromagnetic spectrum (EMS) and networking systems for a variety of tasks. But these wireless systems are found to be vulnerable to attacks. In this paper we focus on coping with the jamming attack and propose a new jamming-resistant communication scheme by leveraging the idea of cryptographic secret sharing, which can be further used together with existing defenses such as direct sequence spread spectrum (DSSS) and frequency hopping spread spectrum (FHSS). We characterize the effectiveness of the resulting schemes, leading to a number of findings.

Abstract Semantic segmentation has been proposed as a tool to accelerate the processing of natural history collection images. However, developing a flexible and resilient segmentation network requires an approach for adaptation which allows processing different datasets with minimal training and validation. This paper presents a cross-validation approach designed to determine whether a semantic segmentation network possesses the flexibility required for application across different collections and institutions. Consequently, the specific objectives of cross-validating the semantic segmentation network are to (a) evaluate the effectiveness of the network for segmenting image sets derived from collections different from the one in which the network was initially trained on; and (b) test the adaptability of the segmentation network for use in other types of collections. The resilience to data variations from different institutions and the portability of the network across different types of collections are required to confirm its general applicability. The proposed validation method is tested on the Natural History Museum semantic segmentation network, designed to process entomological microscope slides. The proposed semantic segmentation network is evaluated through a series of cross-validation experiments designed to test using data from two types of collections: microscope slides (from three institutions) and herbarium sheets (from seven institutions). The main contribution of this work is the method, software and ground truth sets created for this cross-validation as they can be reused in testing similar segmentation proposals in the context of digitization of natural history collections. The cross-validation of segmentation methods should be a required step in the integration of such methods into image processing workflows for natural history collections.

This paper is concerned with finding optimal decompositions of transformation graphs. These directed graphs can be regarded as state transition graphs of autonomous sequential networks.

An important aspect of the packaging of digital networks is the allocation of logic gates to modules such that a predetermined objective function is minimized. In order to develop techniques for this partitioning of a logic network we have considered the following problem: Given an acyclic combinational network composed of various primitive blocks such as NOR gates, assume that a maximum of M gates can be "clustered" together into larger modules, and that a maximum of P pins can be accommodated in each larger module. Assume also that in a network composed of such larger modules, no delay is encountered on the interconnections linking two gates internal to a module and a delay of one time unit is encountered on interconnections linking two gates in different modules . Find an easily applied algorithm that will result in a network such that the maximum delay through the network is minimized.

Abstract—Autonomous sequential networks are represented by transformation graphs, i.e., finite directed graphs, each vertex of which has outdegree one. A network that can be realized by a set of simpler, parallel networks corresponds to a transformation graph representable as a Cartesian product of simpler graphs. An algorithm for obtaining the various decompositions of a given transformation graph into irreducible factors is presented. The particular decomposition into a minimum number of factors is directly reached by the method. Decompositions into a greater number of factors are also obtained so that a balance may be struck between number and complexity of factors.