Deep reinforcement learning (DRL) has achieved outstanding results in recent years. This has led to a dramatic increase in the number of applications and methods. Recent works have explored learning beyond single-agent scenarios and have considered multiagent scenarios. Initial results report successes in complex multiagent domains, although there are several challenges to be addressed. In this context, first, this article provides a clear overview of current multiagent deep reinforcement learning (MDRL) literature. Second, it provides guidelines to complement this emerging area by (i) showcasing examples on how methods and algorithms from DRL and multiagent learning (MAL) have helped solve problems in MDRL and (ii) providing general lessons learned from these works. We expect this article will help unify and motivate future research to take advantage of the abundant literature that exists in both areas (DRL and MAL) in a joint effort to promote fruitful research in the multiagent community.

Transfer learning is a widely used strategy in medical image analysis. Instead of only training a network with a limited amount of data from the target task of interest, we can first train the network with other, potentially larger source datasets, creating a more robust model. The source datasets do not have to be related to the target task. For a classification task in lung CT images, we could use both head CT images, or images of cats, as the source. While head CT images appear more similar to lung CT images, the number and diversity of cat images might lead to a better model overall. In this survey we review a number of papers that have performed similar comparisons. Although the answer to which strategy is best seems to be "it depends", we discuss a number of research directions we need to take as a community, to gain more understanding of this topic.

There are a lot of different kinds of machine learning, and some of them are not based exclusively on deep neural networks that learn from tagged text, audio, image, and video data to analyze and sometimes transpose that data into a different form. In the business world, companies have to work with numbers, culled from interactions with millions or billions of customers, and providing GPU acceleration for this style of machine learning is just as vital as the types mentioned above. Up until now, many of the popular machine learning tools, which are open source, have been exclusively used on workstations or servers that used CPUs as their processing engines. To be fair, the SIMD engines inside of many popular CPUs have been supported with many of these tools, the Apache Arrow columnar database being an important one that often underpins the data scientist workbench; the Apache Spark in-memory database has been tweaked to make use of SIMD and vector units and also has other means of acceleration by compiling down to C instead of Java. But with the launch of Rapids, a collection of integrated machine learning tools that are popular among data scientists, Nvidia and the communities that maintain these tools are providing the same kind of acceleration that HPC simulation and modeling and machine learning neural network training have enjoyed for years.

While deep learning, machine learning and artificial intelligence (AI) may seem to be used synonymously, there are clear differences. One school of thought is that artificial intelligence is a larger umbrella category under which machine learning falls and deep learning falls under machine learning. Therefore, while everything that is categorized as deep learning or machine learning is part of the artificial intelligence field, not everything that is machine learning will be deep learning. Now that we've discussed the big picture, let's dive into the parent category: artificial intelligence. AI as a theoretical concept has been around for over a hundred years but the concept that we understand today was developed in the 1950s and refers to intelligent machines that work and react like humans.

In March 2016, AlphaGo's deep learning algorithms ruthlessly dethroned mankind's best Go player. The whole world jittered, knowing that the same job-eating AI technology was coming soon to an office near everyone. Civilization has absorbed economic shocks driven by technology in the past, turning hundreds of millions of farmers into factory workers over the 19th and 20th centuries. However, these structural changes didn't arrive as quickly as the breakneck pace we're currently experiencing with AI. Based on current trends in technology advancement and adoption, I predict that within 15 years, AI will theoretically be able to replace 40% to 50% of jobs in the United States.

DeepMind has struck a critical new partnership with Unity Technologies, the game-development platform used by half the world's mobile games, including Temple Run and Hearthstone: Heroes of Warcraft, and it's one that could also help its nascent business. For now, it will take DeepMind's research on deep-reinforcement learning to the next level, says Danny Lange, vice president of AI at Unity, who spoke to Forbes from the sidelines of the O'Reilly AI conference in London on Wednesday. Deep-reinforcement learning is an approach to AI that trains an algorithm with positive and negative signals. Unity already has a freely available toolkit for training independent agents in a simulation (an approach to AI for training a neural network), but this partnership represents something more--a "deep collaboration between our teams," says Lange. "We are working with DeepMind to enable them to have [a virtual worlds] environment." "It opens the door for dealing with realistic and complex problems," he adds.

"As we rely more and more on these systems, it is important to know how they work and why," said Cameron Buckner, assistant professor of philosophy and author of a paper exploring the topic published in the journal Synthese. Better understanding how the systems work, in turn, led him to insights into the nature of human learning. Philosophers have debated the origins of human knowledge since the days of Plato -- is it innate, based on logic, or does knowledge come from sensory experience in the world? Deep Convolutional Neural Networks, or DCNNs, suggest human knowledge stems from experience, a school of thought known as empiricism, Buckner concluded. These neural networks -- multi-layered artificial neural networks, with nodes replicating how neurons process and pass along information in the brain -- demonstrate how abstract knowledge is acquired, he said, making the networks a useful tool for fields including neuroscience and psychology.

We have a paradox staring us in the face. All that web content creates a great forum for philosophical debate: Will AI save the world or bring about the extinction of homo sapiens? Compelling research demos often show super-human performance on selected cognitive tasks, especially perception and pattern recognition in image, streams, audio, and transaction data. Thus, the possible outcomes also include affordable solutions for complex social problems, advanced diagnosis and treatment of medical conditions, environmental sustainability efforts, climate optimized traffic flow and safety, and cybercrime and fraud prevention. And of course, businesses everywhere appear to be fully expecting to put AI to work in some form as soon as possible.

Here are the most popular posts in KDnuggets in September, based on the number of unique page views (UPV), and social share counts from Facebook, Twitter, and Addthis. Most Shareable (Viral) Blogs Among the top blogs, here are the 5 blogs with the highest ratio of shares/unique views, which suggests that people who read it really liked it. You Aren't So Smart: Cognitive Biases are Making Sure of It, by Matthew Mayo A Winning Game Plan For Building Your Data Science Team, by William Schmarzo What on earth is data science?, by Cassie Kozyrkov Everything You Need to Know About AutoML and Neural Architecture Search, by George Seif The Data Science of "Someone Like You" or Sentiment Analysis of Adele's Songs, by Preetish Panda How many data scientists are there and is there a shortage?, by Gregory Piatetsky Neural Networks and Deep Learning: A Textbook, by Charu Aggarwal 5 Resources to Inspire Your Next Data Science Project, by Conor Dewey Hadoop for Beginners, by Aafreen Dabhoiwala 6 Steps To Write Any Machine Learning Algorithm From Scratch: Perceptron Case Study, by John Sullivan Deep Learning for NLP: An Overview of Recent Trends, by Elvis Saravia (*) Ultimate Guide to Getting Started with TensorFlow, by Brian Zhang (*) How many data scientists are there and is there a shortage?, by Gregory Piatetsky Essential Math for Data Science: 'Why' and'How', by Tirthajyoti Sarkar Journey to Machine Learning - 100 Days of ML Code, by Avik Jain You Aren't So Smart: Cognitive Biases are Making Sure of It, by Matthew Mayo Neural Networks and Deep Learning: A Textbook, by Charu Aggarwal (*) You Aren't So Smart: Cognitive Biases are Making Sure of It, by Matthew Mayo How many data scientists are there and is there a shortage?, by Gregory Piatetsky You Aren't So Smart: Cognitive Biases are Making Sure of It, by Matthew Mayo A Winning Game Plan For Building Your Data Science Team, by William Schmarzo What on earth is data science?, by Cassie Kozyrkov Everything You Need to Know About AutoML and Neural Architecture Search, by George Seif The Data Science of "Someone Like You" or Sentiment Analysis of Adele's Songs, by Preetish Panda You Aren't So Smart: Cognitive Biases are Making Sure of It, by Matthew Mayo What on earth is data science?, by Cassie Kozyrkov

I have three dogs at home. The youngest, who is still a puppy, is threatening to demolish our living room couch. I'd like to know when my furry terminator gets into demolition mode so that I can salvage the situation. The trouble is that we cannot monitor the living room round the clock. While I can arm the webcam with motion detection capabilities, I need to be alerted about a specific kind of motion.