In this paper, we consider the problem of learning a policy by observing numerous non-expert agents. Our goal is to extract a policy that, with high-confidence, acts better than the average agents' performance. Such a setting is important for real-world problems where expert data is scarce but non-expert data can easily be obtained, e.g. by crowdsourcing. Our approach is to pose this problem as safe policy improvement in Reinforcement Learning. First, we evaluate an average behavior policy and approximate its value function. Then, we develop a stochastic policy improvement algorithm, termed Rerouted Behavior Improvement (RBI), that safely improves the average behavior. The primary advantages of RBI over current safe learning methods are its stability in the presence of value estimation errors and the elimination of a policy search process. We demonstrate these advantages in a Taxi grid-world domain and in four games from the Atari learning environment.

This paper presents a locally decoupled network parameter learning with local propagation. Three elements are taken into account: (i) sets of nonlinear transforms that describe the representations at all nodes, (ii) a local objective at each node related to the corresponding local representation goal, and (iii) a local propagation model that relates the nonlinear error vectors at each node with the goal error vectors from the directly connected nodes. The modeling concepts (i), (ii) and (iii) offer several advantages, including (a) a unified learning principle for any network that is represented as a graph, (b) understanding and interpretation of the local and the global learning dynamics, (c) decoupled and parallel parameter learning, (d) a possibility for learning in infinitely long, multi-path and multi-goal networks. Numerical experiments validate the potential of the learning principle. The preliminary results show advantages in comparison to the state-of-the-art methods, w.r.t. the learning time and the network size while having comparable recognition accuracy.

Object detection is a domain that has benefited immensely from the recent developments in deep learning. Recent years have seen people develop many algorithms for object detection, some of which include YOLO, SSD, Mask RCNN and RetinaNet. For the past few months, I've been working on improving object detection at a research lab. One of the biggest takeaways from this experience has been realizing that the best way to go about learning object detection is to implement the algorithms by yourself, from scratch. This is exactly what we'll do in this tutorial.

Adam Coates is the Director of Baidu's Silicon Valley AI Lab. Craig Cannon [00:00] – Hey, this is Craig Cannon, and you're listening to Y Combinator's podcast. This episode is with Adam Coates. Adam's the director of Baidu's Silicon Valley AI Lab, and what they focus on is developing AI technologies that'll impact at least 100 million people. We spent a good chunk of this episode talking about Adam's work in speech to text and text to speech, so if you want to learn more about those projects, you can check out research.baidu.com, Today we have Adam Coates here for an interview. Adam, you run the AI lab at Baidu, in Silicon Valley. Could you just give us a quick intro and explain with Baidu is for people who don't know? Adam Coates [00:40] – Yeah, Baidu is actually the largest search engine in China. So it turns out the internet ecosystem in China is this incredibly dynamic environment. So Baidu, I think, turned out to be an early technology leader and really established itself in PC search, but then also has remade itself in the mobile revolution, and increasingly, today, is becoming an AI company, recognizing the value of AI for a whole bunch of different applications, not just search.

In application-development circles, containers have gotten a lot of attention in recent years -- for many good reasons. To name a few advantages, containers simplify and accelerate the process of building and isolating applications. They are lightweight and come with low overhead. And they enable easier application sharing and reproducibility, because the container image includes both the application and its development environment. Especially when it comes to deep learning (DL) frameworks, containerization is now rising in importance.

This tutorial takes you along the steps required to create a convolutional neural network (CNN/ConvNet) using TensorFlow and get it into production by allowing remote access via a HTTP-based application using Flask RESTful API. In this tutorial, a CNN is to be built using TensorFlow NN (tf.nn) module. The CNN model architecture is created and trained and tested against the CIFAR10 dataset. To make the model remotely accessible, a Flask Web application is created using Python to receive an uploaded image and return its classification label using HTTP. Anaconda3 is used in addition to TensorFlow on Windows with CPU support.

Artificial intelligence (AI) makes it possible for machines to learn from experience, adjust to new inputs and perform human-like tasks. Most AI examples that you hear about today – from chess-playing computers to self-driving cars – rely heavily on deep learning and natural language processing. Using these technologies, computers can be trained to accomplish specific tasks by processing large amounts of data and recognizing patterns in the data. Join a series of monthly webinars from John Spooner, AI Expert at SAS and colleagues which discuss the practicalities of Artificial Intelligence from hands on experience.

Games have long been used as test beds and benchmarks for artificial intelligence, and there has been no shortage of achievements in recent months. Google DeepMind's AlphaGo and poker bot Libratus from Carnegie Mellon University have both beaten human experts at games that have traditionally been hard for AI – some 20 years after IBM's DeepBlue achieved the same feat in chess. Games like these have the attraction of clearly defined rules; they are relatively simple and cheap for AI researchers to work with, and they provide a variety of cognitive challenges at any desired level of difficulty. By inventing algorithms that play them well, researchers hope to gain insights into the mechanisms needed to function autonomously. With the arrival of the latest techniques in AI and machine learning, attention is now shifting to visually detailed computer games – including the 3D shooter Doom, various 2D Atari games such as Pong and Space Invaders, and the real-time strategy game StarCraft.

According to the GMI Research report, "Global Artificial Intelligence Market By Solution, By Technology, By End-Use, and By Geography -- Opportunities & Forecast 2016–2025", the global artificial intelligence market was estimated to be USD 4,157.6 million in 2016 and is projected to reach USD 153,389.0 million by the end of 2025, exhibiting a CAGR of 49.3% during the forecast period. The key factors boosting the growth of the market are increasing adoption of artificial intelligence solutions across a broad range of industries, the rise in demand for analyzing and interpreting large amounts of data, as well as development and acceptance of technologically advanced artificial intelligence solutions for upgrading consumer services. On the Basis of Solution, Hardware Is Expected to Exhibit the Highest Cagr Through 2025 Surging demand from several industries such as retail, BFSI, healthcare, automotive and transportation, media and advertising, and manufacturing worldwide has led to a burgeoning market growth of hardware solution. This segment typically includes chipsets such as central processing units, graphics processing units, application specific integrated circuits, as well as the field-programmable gate array. Apart from this, the technological advancements, such as superior computing power, parallel computation capabilities, and more storage capacity in AI-enabled hardware products are further likely to drive the growth of this segment.

Variational autoencoders and GANs have been 2 of the most interesting developments in deep learning and machine learning recently. Yann LeCun, a deep learning pioneer, has said that the most important development in recent years has been adversarial training, referring to GANs. GAN stands for generative adversarial network, where 2 neural networks compete with each other. Unsupervised learning means we're not trying to map input data to targets, we're just trying to learn the structure of that input data. Once we've learned that structure, we can do some pretty cool things.