394 research outputs found
A deep convolutional neural network for breast density assessment: Optimization and explainability.
No full textThis work aims to develop a method for deep neural network explainability. It is the ability to explain the algorithm behaviour and its predictions when it has a deep multi-layer nonlinear structure. This is a critical issue in Artificial Intelligence. An already developed deep Residual Convolutional Neural Network is able to automatically classify mammograms into breast density classes. The explainability of the network has been studied through various analyses and visualization techniques, assessing trust in the model, which is fundamental for its potential application in clinical practice, and also achieving a performance improvement in terms of accuracy
Speculation in commodities: Keynes practical acquaintance with futures markets
No full textIn this paper we address the subject of Keynes as a speculator. We look first at the primary sources of information, which are in the form of unpublished letters and brokers statements. Secondly, we look at the theory Keynes sparingly presented in his writings, but which nevertheless is grounded on his first-hand knowledge of speculative behavior. Thirdly, we examine the focus on speculation in commodities, which had great weight in his portfolio, and have chosen a particular commodity -wheat- for our investigation. In particular, we examine some of Keyness dealings in wheat futures with the aim of shedding light on the underlying investment strategy. © 2010 The History of Economics Society
Explainability of a CNN for breast density assessment
No full textDeep neural network explainability is a critical issue in Artificial Intelligence (AI). This work aims to develop a method to explain a deep residual Convolutional Neural Network able to automatically classify mammograms into breast density classes. Breast density, a risk factor for breast cancer, is defined as the amount of fibroglandular tissue compared to fat tissue visible on a mammogram. We studied the explainability of the classifier to understand the reasons behind its predictions, in fact with a deep multi-layer structure, it acts like a black-box. As there is no well-established method, we explored different possible analyses and visualization techniques. The main obtained results were the achievement of a performance improvement in terms of accuracy and a contribution to assess trust in the model. This is fundamental for a potential application in clinical practice
Moneta internazionale. Un piano per la libertà del commercio e il disarmo finanziario
No full textNo abstract availabl
Mammona: la falsa virtù del risparmio
No full textIn un famoso passo de La riforma monetaria, J. M. Keynes descrive come, nel XIX secolo, Dio e mammona si fossero riconciliati nella virtù assieme politica, morale e religiosa del risparmio. In effetti, a partire dall’Ottocento, in consonanza con l’etica economica emergente, anche la Chiesa predica il risparmio. Le istituzioni finanziarie d’ispirazione cristiana hanno seguito l’evoluzione dottrinale: i Monti di Pietà, fondati dai francescani nel Quattrocento, fornivano prestiti su pegno ai bisognosi, senza interesse; nell’Ottocento, le Casse di Risparmio premiano con l’interesse la parsimonia dei lavoratori, rendendoli partecipi dei benefici dell’accumulazione. La Chiesa si è associata così all’elogio del risparmio, nonostante la condanna irrefutabile delle Scritture contro ogni forma di accumulazione. Mammona non è semplicemente la ricchezza: il termine aramaico sembra indicare piuttosto l’ammasso di ricchezza, il tesoro, ciò che è posto al sicuro, in un deposito. L’ipotesi trova conferma esplicita in molteplici passi della Scrittura, dove alla ricchezza è posto un limite preciso: nessuno deve possedere più di quanto può consumare. La giusta misura della proprietà è data dalla possibilità del consumo. Mammona non è il denaro in quanto tale, ma il denaro in quanto riserva di valore. La buona moneta è quella che misura il valore a partire da un lavoro compiuto e in vista del consumo. Per secoli la moneta è stata principalmente questa misura del valore, in vista della distribuzione secondo il bisogno. Soltanto in epoca moderna la moneta è diventata riserva di valore. L’inflazione sopperisce, in maniera parziale e disordinata, al fatto che la moneta, a differenza di ogni altro bene utile alla vita, non deperisce. “Ed è in tal modo che si deve impedire il formarsi di patrimoni perpetui, a meno che la società deliberatamente non provveda ad impedirlo in qualche altro modo più equo e più opportuno” (ancora Keynes, 1923). Come l’anno sabbatico, il giubileo o la decumulazione sistematica della moneta nel dono
The Clearing Union as Keynes’s intellectual testament
No full textThis chapter explains that Keynes's Clearing Union represents the coherent and accomplished result of his lifelong speculation on how national economies should approach the complexity of their interconnectedness, as well as on how they can be helped by a supportive international architecture to achieve their targets. The seeds of Keynes's plan were sown over the previous thirty years. The main ideas that eventually gave shape to the proposal can be detected throughout his previous works, in significant passages of Keynes's theoretical writings, correspondence, articles, and proposals to reform the international monetary system. Free trade was established as a fundamental principle of the postwar economic order by the Atlantic Charter. For Britain, it implied renouncing the Imperial preference. The Clearing Union was intended to finance temporary current account imbalances, while restricting movements on capital account. Keynes proposed an adjustable pegs regime, as a kind of intermediate solution between fixed and flexible exchange rates
Speculation in commodities: Keynes practical acquaintance with futures markets
No full textIn this paper we address the subject of Keynes as a speculator. We look first at the primary sources of information, which are in the form of unpublished letters and brokers statements. Secondly, we look at the theory Keynes sparingly presented in his writings, but which nevertheless is grounded on his first-hand knowledge of speculative behavior. Thirdly, we examine the focus on speculation in commodities, which had great weight in his portfolio, and have chosen a particular commodity -wheat- for our investigation. In particular, we examine some of Keyness dealings in wheat futures with the aim of shedding light on the underlying investment strategy. © 2010 The History of Economics Society
An automatic system to discriminate malignant from benign massive lesions on mammograms
No full textMammography is widely recognized as the most reliable technique for early detection of breast cancers. Automated or semi-automated computerized classification schemes can be very useful in assisting radiologists with a second opinion about the visual diagnosis of breast lesions, thus leading to a reduction in the number of unnecessary biopsies. We present a computer-aided diagnosis (CADi) system for the characterization of massive lesions in mammograms, whose aim is to distinguish malignant from benign masses. The CADi system we realized is based on a three-stage algorithm: (a) a segmentation technique extracts the contours of the massive lesion from the image; (b) 16 features based on size and shape of the lesion are computed; (c) a neural classifier merges the features into an estimated likelihood of malignancy. A data set of 226 massive lesions (109 malignant and 117 benign) has been used in this study. The system performances have been evaluated in terms of the receiver-operating characteristic (ROC) analysis, obtaining A(z) = 0.80 +/- 0.04 as the estimated area under the ROC curve. (c) 2006 Elsevier B.V. All rights reserved. RI Retico, Alessandra /I-6321-201
An automatic system to discriminate malignant from benign massive lesions in mammograms
No full textEvaluating the degree of malignancy of a massive lesion on the basis of the mere visual analysis of the mammogram is a non-trivial task. We developed a semi-automated system for massive-lesion characterization with the aim to support the radiological diagnosis. A dataset of 226 masses has been used in the present analysis. The system performances have been evaluated in terms of the area under the ROC curve, obtaining Az= 0.80 ± 0.04
- …
