The stochastic gradient descent (SGD) optimization algorithm plays a central role in machine learning and, in particular, deep learning applications such as image analysis and speech recognition (cf., e.g., [12, 13, 16, 23]). It is therefore important to analyze and quantify the convergence speed of the SGD method. There is a vast amount of scientific literature investigating and providing upper bounds for the SGD method and modifications of it (cf., e.g., [3, 4, 5, 6, 7, 8, 9, 10, 11, 18, 20, 21, 24] and cf., e.g., [14] for a more comprehensive review of the literature). Much less attention has been paid to proving lower error bounds for the SGD method, that is, to quantifying the best possible speed of convergence which the SGD method can achieve (cf., e.g., [2, 17, 19, 22, 25]). It is the key contribution of this paper to make a step in this direction.

This morning, MIT Technology Review published its 18th-annual 10 Breakthrough Technologies list, and it includes some fascinating entries. By "breakthrough," the publication means "a technology, or perhaps even a collection of technologies, that will have a profound effect on our lives." Now that we have our definitions out of the way, let's take a look at some of the technologies that our kids will probably see as old-hat, but that we'll consider truly innovative. With the possibility of using metals as well as plastic, composites, and other materials, 3D printing companies will make it easier than ever for businesses to print replacement parts, or even all-new ones. And that means they don't have to keep huge inventories of things they might someday need.

After decades of promise and hype, artificial intelligence has finally reached a tipping point of market acceptance. Every day we can read about the latest AI advances and applications from startups and large companies. AI was the star of the 2018 Consumer Electronic Show earlier this year in Las Vegas. But, despite its market acceptance, a recent McKinsey report found that AI adoption is still at an early, experimental stage, especially outside the tech sector. Based on a survey of over 3,000 AI-aware C-level executives across 10 countries and 14 sectors, the report found that 20 percent of respondents had adopted AI at scale in a core part of their business, 40 percent were partial adopters or experimenters, while another 40 percent were still waiting to take their first steps.

Internet of Things (IoT) technologies have made considerable recent advances in commercial applications, prompting new research on their use in military applications. Towards the development of an Internet of Battlefield Things (IoBT), capable of leveraging mixed commercial and military technologies, several unique challenges of the tactical environment present themselves. These challenges include development of methods for: (I) quickly gathering training data reflecting unforeseen learning/classification tasks; (II) incrementally learning over real-time data streams; (III) management of limited network bandwidth and connectivity between IoBT assets in data gathering and classification tasks. This paper provides a survey over classical and modern statistical learning theory, and how numerical optimization can be used to solve corresponding mathematical problems. The objective of this paper is to encourage the IoT and machine learning research communities to revisit the underlying mathematical underpinnings of stream-based learning, as applicable to IoBT-based systems.

Today, the amount of data that can be retrieved from communications networks is extremely high and diverse (e.g., data regarding users behavior, traffic traces, network alarms, signal quality indicators, etc.). Advanced mathematical tools are required to extract useful information from this large set of network data. In particular, Machine Learning (ML) is regarded as a promising methodological area to perform network-data analysis and enable, e.g., automatized network self-configuration and fault management. In this survey we classify and describe relevant studies dealing with the applications of ML to optical communications and networking. Optical networks and system are facing an unprecedented growth in terms of complexity due to the introduction of a huge number of adjustable parameters (such as routing configurations, modulation format, symbol rate, coding schemes, etc.), mainly due to the adoption of, among the others, coherent transmission/reception technology, advanced digital signal processing and to the presence of nonlinear effects in optical fiber systems. Although a good number of research papers have appeared in the last years, the application of ML to optical networks is still in its early stage. In this survey we provide an introductory reference for researchers and practitioners interested in this field. To stimulate further work in this area, we conclude the paper proposing new possible research directions.

Researchers have developed cognitive systems capable of human-level performance at complex tasks (e.g., Watson and AlphaGo), but constructing these systems required substantial time and expertise. To address this challenge, a new line of research has begun to coalesce around the concept of cog-nitive systems that users can teach rather than program. A key goal of this research is to develop natural approaches for end users to directly train these systems to perform new tasks. However, what makes training interactions natural remains an open research question that we begin to explore in this paper. To lay the foundation for this exploration, we review the human-computer interaction literature to identify characteristics of systems that have historically been natural for end users to interact with. Based on this review, we propose a framework for cognitive system training interactions that decomposes interaction into patterns, types, and modalities, all of which support the acquisition of different kinds of knowledge. Finally, we discuss how this framework characterizes existing research within this space and how it can guide future research.

Knowledge Graph Embedding methods aim at representing entities and relations in a knowledge base as points or vectors in a continuous vector space. Several approaches using embeddings have shown promising results on tasks such as link prediction, entity recommendation, question answering, and triplet classification. However, only a few methods can compute low-dimensional embeddings of very large knowledge bases. In this paper, we propose KG2Vec, a novel approach to Knowledge Graph Embedding based on the skip-gram model. Instead of using a predefined scoring function, we learn it relying on Long Short-Term Memories. We evaluated the goodness of our embeddings on knowledge graph completion and show that KG2Vec is comparable to the quality of the scalable state-of-the-art approaches and can process large graphs by parsing more than a hundred million triples in less than 6 hours on common hardware.

Industrial robots are primarily known from the automotive industry's production lines. The goal of this class is to present robots instead as multifunctional and flexible interfaces between the digital and the physical world that can be used for anything from innovative, large-scale fabrication to immersive virtual reality (VR) simulators. This extension beyond the robots' initial scope is enabled by new software developments that facilitate a seamless workflow from design to machine through Dynamo software and KUKA prc. Utilizing parametric design tools lets us use robots for mass customization and small lot sizes, rather than mass fabrication. The class will provide an overview on how to utilize industrial robots through Dynamo and Fusion 360 software, and present realized projects by both small to medium-size enterprises as well as international corporations.

Deep learning is having a large impact on the field of natural language processing. But, as a beginner, where do you start? Both deep learning and natural language processing are huge fields. What are the salient aspects of each field to focus on and which areas of NLP is deep learning having the most impact? In this post, you will discover a primer on deep learning for natural language processing.

When it comes to revolutionary technology, the blockchain and cognitive computing are two at the top of the list in 2018. With these technologies finally being put to use in practical applications, we're learning more and more about what they can do on their own--and together. Let's take a look at how some industries can take advantage of this powerful combination. Before we can discuss what these two technologies can accomplish together, it's important to understand them separately. Cognitive computing is essentially using advanced artificial intelligence systems to create a "thinking" computer.