Because of their effectiveness in broad practical applications, LSTM networks have received a wealth of coverage in scientific journals, technical blogs, and implementation guides. However, in most articles, the inference formulas for the LSTM network and its parent, RNN, are stated axiomatically, while the training formulas are omitted altogether. In addition, the technique of "unrolling" an RNN is routinely presented without justification throughout the literature. The goal of this paper is to explain the essential RNN and LSTM fundamentals in a single document. Drawing from concepts in signal processing, we formally derive the canonical RNN formulation from differential equations. We then propose and prove a precise statement, which yields the RNN unrolling technique. We also review the difficulties with training the standard RNN and address them by transforming the RNN into the "Vanilla LSTM" network through a series of logical arguments. We provide all equations pertaining to the LSTM system together with detailed descriptions of its constituent entities. Albeit unconventional, our choice of notation and the method for presenting the LSTM system emphasizes ease of understanding. As part of the analysis, we identify new opportunities to enrich the LSTM system and incorporate these extensions into the Vanilla LSTM network, producing the most general LSTM variant to date. The target reader has already been exposed to RNNs and LSTM networks through numerous available resources and is open to an alternative pedagogical approach. A Machine Learning practitioner seeking guidance for implementing our new augmented LSTM model in software for experimentation and research will find the insights and derivations in this tutorial valuable as well.

Abstract-- Open-Source Projects and Libraries are being used in software development while also bearing multiple security vulnerabilities. This use of third party ecosystem creates a new kind of attack surface for a product in development. An intelligent attacker can attack a product by exploiting one of the vulnerabilities present in linked projects and libraries. In this paper, we mine threat intelligence about open source projects and libraries from bugs and issues reported on public code repositories. We also track library and project dependencies for installed software on a client machine. We represent and store this threat intelligence, along with the software dependencies in a security knowledge graph. Security analysts and developers can then query and receive alerts from the knowledge graph if any threat intelligence is found about linked libraries and projects, utilized in their products. I. INTRODUCTION In the normal course of software development, developers and coders rely on various open source projects and libraries. Open source projects and libraries comprise of source code that is open for anyone to inspect, modify, update or enhance [17].

Vision is a common source of inspiration for poetry. The objects and the sentimental imprints that one perceives from an image may lead to various feelings depending on the reader. In this paper, we present a system of poetry generation from images to mimic the process. Given an image, we first extract a few keywords representing objects and sentiments perceived from the image. These keywords are then expanded to related ones based on their associations in human written poems. Finally, verses are generated gradually from the keywords using recurrent neural networks trained on existing poems. Our approach is evaluated by human assessors and compared to other generation baselines. The results show that our method can generate poems that are more artistic than the baseline methods. This is one of the few attempts to generate poetry from images. By deploying our proposed approach, XiaoIce has already generated more than 12 million poems for users since its release in July 2017. A book of its poems has been published by Cheers Publishing, which claimed that the book is the first-ever poetry collection written by an AI in human history.

Ticket assignment/dispatch is a crucial part of service delivery business with lot of scope for automation and optimization. In this paper, we present an end-to-end automated helpdesk email ticket assignment system, which is also offered as a service. The objective of the system is to determine the nature of the problem mentioned in an incoming email ticket and then automatically dispatch it to an appropriate resolver group (or team) for resolution. The proposed system uses an ensemble classifier augmented with a configurable rule engine. While design of classifier that is accurate is one of the main challenges, we also need to address the need of designing a system that is robust and adaptive to changing business needs. We discuss some of the main design challenges associated with email ticket assignment automation and how we solve them. The design decisions for our system are driven by high accuracy, coverage, business continuity, scalability and optimal usage of computational resources. Our system has been deployed in production of three major service providers and currently assigning over 40,000 emails per month, on an average, with an accuracy close to 90% and covering at least 90% of email tickets.

We present a regression technique for data driven problems based on polynomial chaos expansion (PCE). PCE is a popular technique in the field of uncertainty quantification (UQ), where it is typically used to replace a runnable but expensive computational model subject to random inputs with an inexpensive-to-evaluate polynomial function. The metamodel obtained enables a reliable estimation of the statistics of the output, provided that a suitable probabilistic model of the input is available. In classical machine learning (ML) regression settings, however, the system is only known through observations of its inputs and output, and the interest lies in obtaining accurate pointwise predictions of the latter. Here, we show that a PCE metamodel purely trained on data can yield pointwise predictions whose accuracy is comparable to that of other ML regression models, such as neural networks and support vector machines. The comparisons are performed on benchmark datasets available from the literature. The methodology also enables the quantification of the output uncertainties and is robust to noise. Furthermore, it enjoys additional desirable properties, such as good performance for small training sets and simplicity of construction, with only little parameter tuning required. In the presence of statistically dependent inputs, we investigate two ways to build the PCE, and show through simulations that one approach is superior to the other in the stated settings.

Global chip maker Intel trained 99,000 developers, students and professors in Artificial Intelligence (AI) since April 2017 for ready talent in India, said the US-based firm on Wednesday. "We have trained over 99,000 developers, students and professors since April 2017 for making AI-ready talent available in the country," said Intel India in a statement in Bengaluru. To mark the occasion, the semi-conductor firm held a developers conference in this tech hub where 500 developers, including experts in data science, machine learning, application development and research participated. "The conference served as a platform to share updates on real-world applications of AI that can benefit businesses and people, said the statement. Intel will also speed up accessibility of AI tools across industries and drive the next wave of computing by investing in developer education.

Samsung Electronics plans to spend $22 billion over the next three years on artificial intelligence, auto components and other future businesses as the company maps out its strategy under the restored leadership of Vice Chairman Lee Jae-yong after he was freed from prison. Samsung said it will spend the sum, amounting to 25 trillion won, on hiring artificial intelligence researchers in about 1,000 artificial intelligence centers around the world, on ensuring it will be a global player in next-generation telecoms technology called 5G and on deepening its involvement in electronic components for future cars. "Samsung expects innovations powered by AI technology will drive the industry's transformation, while the next-generation 5G telecommunications technology will create new opportunities in autonomous driving, the Internet of Things (IoT) and robotics," the company said in a statement. Some of the funding will go to Samsung's biopharmaceutical businesses. Samsung has been beefing up its contract drug-making operations to help counter a potential decline in its mainstay electronics businesses.

Interesting post from We Are Social's Chief Strategy Officer Mobbie Nazir recently. In her post, Mobbie argues that women and diverse minorities should be included in the development of artificial intelligence algorithms, including machine learning. As with many things in this world, women are under-represented in the technology space (I would argue under-represented in any role that is reasonably well paid and certainly at senior manager and above levels). But the development of superior intelligence needs to have more than male voices, be they Anglo-Saxon, Indian or Chinese. I think the fact that the EU is looking very closely at AI, and wanting to be a major player in its development, augers well for the inclusion of normally-excluded voices.

A microchip security flaw has put tens of millions of Samsung Galaxy S7 smartphones at risk to hackers, prompting cyber security experts to issue advice to owners on how best to protect their device. The Meltdown vulnerability, first uncovered by researchers earlier this year, affects computers, smartphones and other smart devices but was initially thought to not affect Samsung Galaxy phones. Meltdown can be exploited by hackers to gain access to a person's private information, including banking details and passwords. The I.F.O. is fuelled by eight electric engines, which is able to push the flying object to an estimated top speed of about 120mph. The giant human-like robot bears a striking resemblance to the military robots starring in the movie'Avatar' and is claimed as a world first by its creators from a South Korean robotic company Waseda University's saxophonist robot WAS-5, developed by professor Atsuo Takanishi and Kaptain Rock playing one string light saber guitar perform jam session A man looks at an exhibit entitled'Mimus' a giant industrial robot which has been reprogrammed to interact with humans during a photocall at the new Design Museum in South Kensington, London Electrification Guru Dr. Wolfgang Ziebart talks about the electric Jaguar I-PACE concept SUV before it was unveiled before the Los Angeles Auto Show in Los Angeles, California, U.S The Jaguar I-PACE Concept car is the start of a new era for Jaguar.

Personal home robots that can socialise with people are starting to roll out of the laboratory and into our living rooms and kitchens. But are humans ready to invite them into their lives? It's taken decades of research to build robots even a fraction as sophisticated as those featured in popular science fiction. They don't much resemble their fictional predecessors; they mostly don't walk, only sometimes roll and often lack limbs. Worse, they're so far losing out to immobile smart speakers made by Amazon, Apple and Google, which cost a fraction of what early social robots do, and which are powered by artificial-intelligence systems that leave many robots' limited abilities in the dust.