Deep reinforcement learning is the combination of reinforcement learning (RL) and deep learning. This field of research has been able to solve a wide range of complex decision-making tasks that were previously out of reach for a machine. Thus, deep RL opens up many new applications in domains such as healthcare, robotics, smart grids, finance, and many more. This manuscript provides an introduction to deep reinforcement learning models, algorithms and techniques. Particular focus is on the aspects related to generalization and how deep RL can be used for practical applications. We assume the reader is familiar with basic machine learning concepts.

Much of machine learning research focuses on producing models which perform well on benchmark tasks, in turn improving our understanding of the challenges associated with those tasks. From the perspective of ML researchers, the content of the task itself is largely irrelevant, and thus there have increasingly been calls for benchmark tasks to more heavily focus on problems which are of social or cultural relevance. In this work, we introduce Kuzushiji-MNIST, a dataset which focuses on Kuzushiji (cursive Japanese), as well as two larger, more challenging datasets, Kuzushiji-49 and Kuzushiji-Kanji. Through these datasets, we wish to engage the machine learning community into the world of classical Japanese literature.

FRAME (Filters, Random fields, And Maximum Entropy) is an energy-based descriptive model that synthesizes visual realism by capturing mutual patterns from structural input signals. The maximum likelihood estimation (MLE) is applied by default, yet conventionally causes the unstable training energy that wrecks the generated structures, which remains unexplained. In this paper, we provide a new theoretical insight to analyze FRAME, from a perspective of particle physics ascribing the weird phenomenon to KL-vanishing issue. In order to stabilize the energy dissipation, we propose an alternative Wasserstein distance in discrete time based on the conclusion that the Jordan-Kinderlehrer-Otto (JKO) discrete flow approximates KL discrete flow when the time step size tends to 0. Besides, this metric can still maintain the model's statistical consistency. Quantitative and qualitative experiments have been respectively conducted on several widely used datasets. The empirical studies have evidenced the effectiveness and superiority of our method.

Tencent is pushing ahead with efforts to sign up schools to use its all-in-one WeChat app as part of a broader shift by the company to go beyond consumers and serve more institutions. Since WeChat started partnering with public schools and private training centres in 2014, students have been to make purchases at canteens, check test scores and communicate in group chats with their peers, parents and teachers using the app's multiple functions. Tencent revamped its organisation structure on the eve of its 20th anniversary this year to align the company to compete for the industrial internet. In an open letter last month, chairman Pony Ma Huateng laid out the rationale for the restructuring, saying that digitisation of the economy meant the battle for the internet has moved on from consumers to industry. "WeChat Pay has been a tool to connect people, and is now increasingly connecting industries under the company's new direction to embrace the industrial internet."

Cutting Edge Deep Learning For Coders, Part 2 from fast.ai

An estimated 4 billion people in the world lack a physical address. Without one, residents lose access to important services like package deliveries, medical care, and disaster relief, as well as the ability to register to vote or obtain a driver's license. Cities also have trouble planning new infrastructure, such as schools, water pipes, and electricity lines. "As you move into a more global economy and more people order and get goods delivered at a distance, you need a more specific address than'the house with the red door across from the cathedral,'" says Merry Law, the president of a company that provides international addressing information. Researchers at the MIT Media Lab and Facebook are now proposing a new way to address the unaddressed: with machine learning.

Ever since the world has become one enormous marketplace, we have seen a constant change in how businesses take place. This has been further fueled by new technologies and rapidly evolving customer expectations. Even the highly regulated banking and finance sector in recent times has witnessed constant metamorphosis of its business models to stay ahead in disruptive times. Hence, when it comes to the financial services ecosystem, the FinTech industry plays a significant role in determining how the sector moves forward. Today, FinTech disruptors are changing how everything works –lending, payments, insurance, credit settlements, and more.

NEW DELHI, DECEMBER 1: Sharing his passion for Machine Learning with Engineering & Technology students, world's youngest IBM Watson programmer, Tanmay Bakshi spoke how Machine Learning takes something so human about us, that is learning, and stimulate that with machines. He was speaking at a'Tech Talk' organized by the Department of Computer Science & Engineering of Sharda University, which witnessed over 250 students participating in the session. During his address, he thanked Sharda University for inviting him and said, "My passion is'Machine Learning' technology, (and) in fact as we speak, this technology is impacting hundreds of fields and hundreds and thousands of lives across the world. It helps us take something so human about us, that is learning, and stimulate that with machines." Tanmay is a 15-year IBM Cloud champion, AI Expert, TED Keynote speaker, and a media personality who has addressed over 200,000 executives, leaders, intellectuals, and developers worldwide at international conferences, schools and universities, financial institutions and multinationals.

Note: This Editorial is appearing in Speaking of Medicine ahead of print. The final version will appear in PLOS Medicine at the end of December. PLOS Medicine Machine Learning Special Issue Guest Editors Suchi Saria, Atul Butte, and Aziz Sheikh cut through the hyperbole with an accessible and accurate portrayal of the forefront of machine learning in clinical translation. Artificial Intelligence (AI) as a field emerged in the 1960s when practitioners across the engineering and cognitive sciences began to study how to develop computational technologies that, like people, can perform tasks such as sensing, learning, reasoning, and taking action. Early AI systems relied heavily on expert-derived rules for replicating how people would approach these tasks.

In a week of multiple nine-figure venture capital funding rounds, B2B FinTech has proved it plans to end the year on a high note. The star of this week's roundup is undoubtedly data: Two Robotics Process Automation (RPA) companies focusing on enterprise data analytics and automation landed a combined $565 million, while other high-value rounds were closed in the workspace sharing and asset-based lending markets. Below, PYMNTS breaks down the more than $912 million raised by B2B FinTech firms this week. RPA is igniting chatter in the corporate finance community as professionals explore next-level analytics and automation functionality to enhance processes like accounts payable, accounts receivable, cash flow management and more. This week, RPA startup Automation Anywhere made waves with its $300 million investment from the SoftBank Vision Fund, reports said Thursday (Nov.