Analysis The ability to think logically and to reason is key to intelligence. When this can be replicated in machines, it will no doubt make AI smarter. But it's a difficult problem, and current methods used in deep learning aren't advanced enough. Deep learning is good for processing information, but it can struggle with reasoning. Enter a different player to the game: relational networks, or RNs.

This paper introduces DeepBach, a graphical model aimed at modeling polyphonic music and specifically hymn-like pieces. We claim that, after being trained on the chorale harmonizations by Johann Sebastian Bach, our model is capable of generating highly convincing chorales in the style of Bach. DeepBach's strength comes from the use of pseudo-Gibbs sampling coupled with an adapted representation of musical data. This is in contrast with many automatic music composition approaches which tend to compose music sequentially. Our model is also steerable in the sense that a user can constrain the generation by imposing positional constraints such as notes, rhythms or cadences in the generated score. We also provide a plugin on top of the MuseScore music editor making the interaction with Deep-Bach easy to use.

The availability of large idea repositories (e.g., the U.S. patent database) could significantly accelerate innovation and discovery by providing people with inspiration from solutions to analogous problems. However, finding useful analogies in these large, messy, real-world repositories remains a persistent challenge for either human or automated methods. Previous approaches include costly hand-created databases that have high relational structure (e.g., predicate calculus representations) but are very sparse. Simpler machine-learning/information-retrieval similarity metrics can scale to large, natural-language datasets, but struggle to account for structural similarity, which is central to analogy. In this paper we explore the viability and value of learning simpler structural representations, specifically, "problem schemas", which specify the purpose of a product and the mechanisms by which it achieves that purpose. Our approach combines crowdsourcing and recurrent neural networks to extract purpose and mechanism vector representations from product descriptions. We demonstrate that these learned vectors allow us to find analogies with higher precision and recall than traditional information-retrieval methods. In an ideation experiment, analogies retrieved by our models significantly increased people's likelihood of generating creative ideas compared to analogies retrieved by traditional methods. Our results suggest a promising approach to enabling computational analogy at scale is to learn and leverage weaker structural representations.

Synapse crossbar is an elementary structure in Neuromorphic Computing Systems (NCS). However, the limited size of crossbars and heavy routing congestion impedes the NCS implementations of big neural networks. In this paper, we propose a two-step framework (namely, group scissor) to scale NCS designs to big neural networks. The first step is rank clipping, which integrates low-rank approximation into the training to reduce total crossbar area. The second step is group connection deletion, which structurally prunes connections to reduce routing congestion between crossbars. Tested on convolutional neural networks of LeNet on MNIST database and ConvNet on CIFAR-10 database, our experiments show significant reduction of crossbar area and routing area in NCS designs. Without accuracy loss, rank clipping reduces total crossbar area to 13.62\% and 51.81\% in the NCS designs of LeNet and ConvNet, respectively. Following rank clipping, group connection deletion further reduces the routing area of LeNet and ConvNet to 8.1\% and 52.06\%, respectively.

Relation network is a noval neural network introduced by deepmind in A simple neural network module for relational reasoning. It can achieve super-human performance in challenging visual question answering datasets such as CLEVR. I implement Relation network using keras and train it on a challenging visual question answering dataset called Cornell NLVR. The training is in progress. The temporal test accuracy is 89.10%, which is much higher than the previous state of the art (61.99%).

At KDnuggets, we try to keep our finger on the pulse of main events and developments in industry, academia, and technology. We also do our best to look forward to key trends on the horizon. We recently asked some of the leading experts in Big Data, Data Science, Artificial Intelligence, and Machine Learning for their opinion on the most important developments of 2016 and key trends they 2017. "What were the main Artificial Intelligence/Machine Learning related events in 2016 and what key trends do you see in 2017?" Common themes include the triumphs of deep neural networks, reinforcement learning's successes, AlphaGo as exemplar of the power of both of these phenomena in unison, the application of machine learning to the Internet of Things, self-driving vehicles, and automation, among others. We generally asked participants to keep their responses to within 100 words or so, but were amenable to longer answers if the situation warranted.

Every company is now a data company, capable of using machine learning in the cloud to deploy intelligent apps at scale, thanks to three machine learning trends: data flywheels, the algorithm economy, and cloud-hosted intelligence. That was the takeaway from the inaugural Machine Learning / Artificial Intelligence Summit, hosted by Madrona Venture Group* last month in Seattle, where more than 100 experts, researchers, and journalists converged to discuss the future of artificial intelligence, trends in machine learning, and how to build smarter applications. With hosted machine learning models, companies can now quickly analyze large, complex data, and deliver faster, more accurate insights without the high cost of deploying and maintaining machine learning systems. "Every successful new application built today will be an intelligent application," Soma Somasegar said, venture partner at Madrona Venture Group. "Intelligent building blocks and learning services will be the brains behind apps."

Two technology trends that drive us are hard to miss. Second is recent and disruptive advancements in Deep Learning and Artificial Intelligence. Messaging Dominance in Mobile There are more than 2.5 billion smart mobile devices in the world, and people are spending more than 80% of their screen time on mobile devices. Messaging is the dominant activity on mobile and in fact, it's the fastest growing activity on mobile devices. The number of users on some of the messaging platforms are staggering, for example, there are more than 1 billion users each on Facebook Messenger and WhatsApp.

Buzzwords can help get a lot of attention on the web. But while these SEO keywords might help people find what they are looking for, they may also add fluff and garbage to searches. Add artificial intelligence (AI), machine learning, neural networks, and deep learning into the mix, and it can be confusing to keep up with which is which. AI: Artificial Intelligence (AI) is usually defined as the science of making computers do things that require intelligence when done by humans. AI has had some success in limited, or simplified, domains (Courtesy of AlanTuring.net).

Deep Genomics is opening doors to understanding the large-scale, incredibly complex data set that makes up the human genome. The Human Genome sequencing project, completed in 2003 cost $3B and took 15 years to complete. Now the human genome can be sequenced within a matter of days for approximately $1,000, making it possible to generate data sets for Deep Genomics. Using artificial intelligence (AI), deep learning algorithms, and complex data sets, the entire healthcare industry could be revolutionized -- from diagnostics to gene therapies to personalized medicine. Deep Genomics holds the key to unlocking the biggest disruptions in the medical, life sciences, and pharmaceutical industries.