Choose an application

• Reference Manager
• EndNote
• RefWorks (Direct export to RefWorks)

Social media has transformed society and the way people interact with each other. The volume and speed in which new content is being generated surpasses the processing capacity of machine learning systems. Analyzing such data demands new approaches coming from natural language processing, text mining, sentiment analysis, etc to understand and resolve the arising challenges. There is a need to develop robust and adaptable systems to tackle these open issues in real time, as well as to provide a meaningful summarization and visualization to the end users. This book provides the reader with a comprehensive overview of the latest developments in social media and machine learning, addressing research innovations, applications, trends, and open challenges in this crucial area.

Machine learning. --- Learning, Machine --- Artificial intelligence --- Machine theory --- Machine learning

Choose an application

• Reference Manager
• EndNote
• RefWorks (Direct export to RefWorks)

Deep learning is a branch of machine learning similar to artificial intelligence. The applications of deep learning vary from medical imaging to industrial quality checking, sports, and precision agriculture. This book is divided into two sections. The first section covers deep learning architectures and the second section describes the state of the art of applications based on deep learning.

Machine learning.

Choose an application

• Reference Manager
• EndNote
• RefWorks (Direct export to RefWorks)

Recent times are witnessing rapid development in machine learning algorithm systems, especially in reinforcement learning, natural language processing, computer and robot vision, image processing, speech, and emotional processing and understanding. In tune with the increasing importance and relevance of machine learning models, algorithms, and their applications, and with the emergence of more innovative uses-cases of deep learning and artificial intelligence, the current volume presents a few innovative research works and their applications in real-world, such as stock trading, medical and healthcare systems, and software automation. The chapters in the book illustrate how machine learning and deep learning algorithms and models are designed, optimized, and deployed. The volume will be useful for advanced graduate and doctoral students, researchers, faculty members of universities, practicing data scientists and data engineers, professionals, and consultants working on the broad areas of machine learning, deep learning, and artificial intelligence.

Machine learning.

Choose an application

• Reference Manager
• EndNote
• RefWorks (Direct export to RefWorks)

Examining the general impact of the Controlled Languages rules in the context of Machine Translation has been an area of research for many years. The present study focuses on the following question: How do the Controlled Language (CL) rules impact the Machine Translation (MT) output individually? Analyzing a German corpus-based test suite of technical texts that have been translated into English by different MT systems, the study endeavors to answer this question at different levels: the general impact of CL rules (rule- and system-independent), their impact at rule level (system-independent), their impact at system level (rule-independent), and at rule and system level. The results of five MT systems (a rule-based system, a statistical system, two differently constructed hybrid systems, and a neural system) are analyzed and contrasted. For this, a mixed-methods triangulation approach that includes error annotation, human evaluation, and automatic evaluation was applied. The data were analyzed both qualitatively and quantitatively based on the following parameters: number and type of MT errors, style and content quality, and scores from two automatic evaluation metrics. In line with many studies, the results show a general positive impact of the applied CL rules on the MT output. However, at rule level, only four rules proved to have positive effects on all parameters; three rules had negative effects on the parameters; and two rules did not show any significant impact. At rule and system level, the rules affected the MT systems differently, as expected. Some rules that had a positive impact on earlier MT approaches did not show the same impact on the neural MT approach. Furthermore, the neural MT delivered distinctly better results than earlier MT approaches, namely the highest error-free, style and content quality rates both before and after the rules application, which indicates that the neural MT offers a promising solution that no longer requires CL rules for improving the MT output, what in turn allows for a more natural style.

Machine translating.

Choose an application

• Reference Manager
• EndNote
• RefWorks (Direct export to RefWorks)

Traditionally associated with craftmanship and manual work, knitwear seems a quite unusual subject of investigation for scientific research. This book places it as an integrative part of the industrial design culture where the dialogue between a productive system of excellence and the design discipline taught in universities becomes a topic of central concern. From an industrial standpoint, knitwear is a fertile ground of technological experimentation while being at the same time one of the most traditional sectors of Made in Italy. The complexity of a long and fragmented production chain is an interesting challenge for designers but affects the training and the knowledge transfer inside companies. On the academic side, the presence of such an industry creates the urgency for higher education to understand how to train knit designers as new professionals, and thus the opportunity for knitwear to be recognized as a discipline deserving specific teaching strategies and a focused scientific research. The present book reports an experimentation conducted in the unique conditions of the Italian industrial design culture, that defined tools and methods to train knit designers not as artists, but with the technical and cultural knowledge and the project-oriented mindset that is typical of industrial design disciplines. These contents are of interest for the academy, as they constitute a tool to design teaching experiences oriented to such a specific industrial sector; for those approaching knitwear design, as it is a pool of information on the complexity of knitwear, a map of the background knowledge, collected and rearranged, and a compass to be guided in building one's own skills; for professionals, who will find here their history, the opinions of colleagues, the opportunity to integrate their knowledge and to learn more about the in-depth experimental, technical and design work that takes place at Politecnico di Milano.

Machine knitting