"In 30 years we're going to look back and say Geoff is Einstein--of AI, deep learning, the thing that we're calling AI," Jacobs says. Hinton's breakthrough, in 1986, was to show that backpropagation could train a deep neural net, meaning one with more than two or three layers. A 2012 paper by Hinton and two of his Toronto students showed that deep neural nets, trained using backpropagation, beat state-of-the-art systems in image recognition. That's the bottom layer of the club sandwich: 10,000 neurons (100x100) representing the brightness of every pixel in the image.

The field of machine learning – and deep learning in particular – has made significant progress recently and use cases for deep learning are becoming more common in the enterprise. We've seen more of our customers adopt machine learning and deep learning frameworks for use cases like natural language processing with free-text data analysis, image recognition systems, threat detection, fraud detection, and more. And as with other use cases in Big Data analytics and data science, they want to run their preferred deep learning frameworks and tools in Docker containers on the BlueData EPIC software platform. So What is Deep Learning? "Deep learning (also known as deep structured learning or hierarchical learning) is part of a broader family of machine learning methods based on learning data representations, as opposed to task-specific algorithms."

Across Europe, insurers spend billions of dollars every year in just claim processing costs, and they need help changing this, according to Lex Tan, founder of insurtech startup MotionsCloud. Tan is one of more than 20 startup founders discussing the insurance market at the annual Intelligent InsurTECH conference on October 3 in London. Click here to find out more. Munich-based MotionsCloud provides an intelligent claims solution for P&C insurers to streamline and automate claims processes. The startup utilises image recognition technology and deep learning technology to identify damage through photos.

Visual Studio Code Tools for AI is a cross-platform extension that supports deep learning frameworks including Microsoft Cognitive Toolkit (CNTK), Google TensorFlow, Theano, Keras, Caffe2 and more. You can use additional deep learning frameworks via the open architecture. Visual Studio Code Tools for AI is integrated with Azure Machine Learning to make it easy to browse through a gallery of sample experiments using CNTK, TensorFlow, MMLSpark and more. This makes it easy to learn and share with others. Visual Studio Code Tools for AI integrates with Azure Machine Learning services to enable submitting deep learning jobs to Azure GPU VMs, Spark clusters and more.

In today's tutorial, I'll demonstrate how you can configure your macOS system for deep learning using Python, TensorFlow, and Keras. This tutorial is the final part of a series on configuring your development environment for deep learning. I created these tutorials to accompany my new book, Deep Learning for Computer Vision with Python; however, you can use these instructions to configure your system regardless if you bought my book or not. In case you're on the wrong page (or you don't have macOS), take a look at the other deep learning development environment tutorials in this series: To learn how to configure macOS for deep learning and computer vision with Python, just keep reading. As you get acclimated in the deep learning domain, you'll want to perform many experiments to hone your skills and even to solve real-world problems.

This article was written by Ian Goodfellow, Yoshua Bengio, and Aaron Courville. It consists of summaries, dozens of formulas, and numerous small sections that will help the beginner quickly grasp the essentials of deep learning. To read the full original article click here. For more deep learning related articles on DSC click here.

While "Big Data" tools such as Spark and MapReduce may offer a resilient way to spread a job out across multiple nodes in such a way that the work can tolerate the failure of a few nodes, some deep learning jobs require that each node stay running until the end of the job, car-sharing service Uber has found. To work with this requirement, Uber has turned to gang scheduling, an optimization algorithm long-known in the field of supercomputing. Gang scheduling ensures that a cluster computing job will run only if all the nodes can be run at the same time, explained Min Cai, Uber staff engineer, during a presentation at MesosCon in Los Angeles last week. Cai was one of the Uber engineers who implemented the gang scheduling algo in an open source framework, called Horovod, for running Google's TensorFlow machine learning software across multiple nodes. Uber uses the software to run training models for deep learning tasks running hundreds of GPUs, for research into guidance for self-driving cars, image classification, and fraud detection.

In this paper, we introduce an approach to automated story generation using Markov Chain Monte Carlo (MCMC) sampling. This approach uses a sampling algorithm based on Metropolis-Hastings to generate a probability distribution which can be used to generate stories via random sampling that adhere to criteria learned by recurrent neural networks. We show the applicability of our technique through a case study where we generate novel stories using an acceptance criteria learned from a set of movie plots taken from Wikipedia. This study shows that stories generated using this approach adhere to this criteria 85%-86% of the time.

In video games, a wide range of characters make up the world players inhabit. These characters, NPCs, have traits, such as their appearance and speech accent, that determine certain things about them, including moral inclination, levels of trustworthiness, social class, levels of education, and ethnic background. But what does an accent say about a character in a video game? We use deep learning to train a neural network to detect speech accents and establish the degree to which machines can be used to recognize these accents. This research aims to help sociolinguists and discourse analysts establish critical study and content analytical findings for instance about stereotypical uses of speech accents, to better analyze who has what accent in video games, and what kind of language ideologies and social value judgments the use of accents in games construct and perpetuate. This paper presents the results of the first deep learning experiments, which were conducted on Standard North American, British Received Pronunciation, and Spanish English. We discuss our methodological considerations and some early deep learning results, which show relatively low levels of accuracy (61%). We discuss possibilities of improving our method, and of enriching our training datasets.

Data-driven approaches to interactive narrative personalization show significant promise for applications in entertainment, training, and education. A common feature of data-driven interactive narrative planning methods is that an enormous amount of training data is required, which is rarely available and expensive to collect from observations of human players. An alternative approach to obtaining data is to generate synthetic data from simulated players. In this paper, we present a long short-term memory (LSTM) neural network framework for simulating players to train data-driven interactive narrative planners. By leveraging a small amount of previously collected human player interaction data, we devise a generative player simulation model. A multi-task neural network architecture is proposed to estimate player actions and experiential outcomes from a single model. Empirical results demonstrate that the bipartite LSTM network produces the better-performing player action prediction models than several baseline techniques, and the multi-task LSTM derives comparable player outcome prediction models within a shorter training time. We also find that synthetic data from the player simulation model contributes to training more effective interactive narrative planners than raw human player data alone.