Ricerc@Sapienza

To improve credit risk management, there is a lot of interest in bankruptcy predictive models. Academic research has mainly used traditional statistical techniques, but interest in the capability of machine learning methods is growing [1][2][3][4]. This Italian case study pursues the goal of developing a commercial firms insolvency prediction model. In compliance with the Basel II Accords, the major objective of the model is an estimation of the probability of default which is the likelihood of a default over a given time horizon, typically one year.

In recent years, computer-assisted diagnostic systems have gained increasing interest through the use of deep learning techniques. In this work we show how it is possible to classify X-ray images through a multi-input convolutional neural network. The use of clinical information together with the images allowed to obtain better results than those present in the literature on the same data.

To improve credit risk management, there is a lot of interest in bankruptcy predictive models. Academic research has mainly used traditional statistical techniques, but interest in the capability of machine learning methods is growing. This Italian case study pursues the goal of developing a commercial firms insolvency prediction model. In compliance with the Basel II Accords, the major objective of the model is an estimation of the probability of default over a given time horizon, typically one year.

In the last few years, computer-assisted diagnosis systems have obtained a growing interest from researchers thanks to the use of deep learning techniques. We propose a deep neural network based on a multi-input architecture that allows to use all the information available to physicians during the diagnosis. The results obtained show an interesting improvement in performance in terms of predictive skill compared to the results in the literature.

Abstract: In recent years, interest has grown in addressing the problem of encoding categorical variables, especially in deep learning applied to big-data. However, the current proposals are not entirely satisfactory. The aim of this work is to show the logic and advantages of a new encoding method that takes its cue from the recent word embedding proposals and which we have called Categorical Embedding. Both a supervised and an unsupervised approach will be considered.

In recent years, computer-assisted diagnostic systems increasingly gained
interest through the use of deep learning techniques. Surely, the medical field could
be one of the best environments in which the power of the AI algorithms can be
tangible for everyone. Deep learning models can be useful to help radiologists elaborate
fast and even more accurate diagnosis or accelerate the triage systems in hospitals.
However, differently from other fields of works, the collaboration and co-work

To assess the microstructural architecture of non-rapid eye movement (NREM) sleep known as cyclic alternating pattern (CAP) in relation to the age, gender, subjective sleep quality and the degree of sleep disruption in large community-based cohort studies of older people.

Beyond sample curation and basic pathologic characterization, the digitized H&E-stained images
of TCGA samples remain underutilized. To highlight this resource, we present mappings of tumorinfiltrating lymphocytes (TILs) based on H&E images from 13 TCGA tumor types. These TIL
maps are derived through computational staining using a convolutional neural network trained to
classify patches of images. Affinity propagation revealed local spatial structure in TIL patterns and

Reverse Engineering (RE) may help tolerance inspection during production by digitalization of analyzed components and their comparison with design requirements. RE techniques are already applied for geometrical and tolerance shape control. Plastic injection molding is one of the fields where it may be applied, in particular for die set-up of multi-cavities, since no severe accuracy is required for the acquisition system. In this field, RE techniques integrated with Computer-Aided tools for tolerancing and inspection may contribute to the so-called “Smart Manufacturing”.

The binary similarity problem consists in determining if two functions are similar considering only their compiled form. Advanced techniques for binary similarity recently gained momentum as they can be applied in several fields, such as copyright disputes, malware analysis, vulnerability detection, etc. In this paper we describe SAFE, a novel architecture for function representation based on a self-attentive neural network.