Current grammar-based NeuroEvolution approaches have several shortcomings. On the one hand, they do not allow the generation of Artificial Neural Networks (ANNs) composed of more than one hidden-layer. On the other, there is no way to evolve networks with more than one output neuron. To properly evolve ANNs with more than one hidden-layer and multiple output nodes there is the need to know the number of neurons available in previous layers. In this paper we introduce Dynamic Structured Grammatical Evolution (DSGE): a new genotypic representation that overcomes the aforementioned limitations. By enabling the creation of dynamic rules that specify the connection possibilities of each neuron, the methodology enables the evolution of multi-layered ANNs with more than one output neuron. Results in different classification problems show that DSGE evolves effective single and multi-layered ANNs, with a varying number of output neurons.

Research reveals a lack of understanding and trust in fintech that is stalling mainstream adoption of innovative new services which could make millions of people's daily lives simpler and more secure. The success of Amazon Echo and Google Home smart speakers show there is a healthy appetite for AI assistance. Autonomous, self-driving cars are in being tested by the likes of Google and Tesla. AI-powered platforms such as IBM Watson and Wipro Holmes are able to diagnose cancer, analyze retail data, and communicate through ordinary spoken and written language. But even though AI feels like it's going mainstream, consumers don't yet fully trust it.

Listen in to this special episode of Charged Up!, taken from a live Facebook broadcast with Jason Schenker, who Bloomberg ranks as the world's foremost financial futurist. In this episode, we talk about Schenker's predictions, laid out in his 2017 book "Jobs for Robots: Between Robocalypse and Robotopia," and how the robot revolution will affect our jobs, our pay and our career prospects. Schenker talks about three industry sectors that are safest from being taken over by technology, what students should study if they're entering school now and what kind of skills will protect you from losing out to robots. So, get Charged Up! about learning how to survive the robot revolution! Jason Schenker: Thank you very much, Jenny. It's a real pleasure to be here. Hoff: So, we're going to talk today about your book, "Jobs for Robots" and this is a live broadcast on Facebook so we're also going to be taking questions from our listeners which I will then later translate for the podcast so we make sure that everybody can hear the questions. But first I want to talk a little bit about how did you get into being a futurist and then where did the interest in robots come from? Schenker: Sure, the most important thing is as a futurist there's three components to it: You're part historian because you need the historical perspective of where we've been.

With products like the Amazon Echo and the upcoming Apple HomePod, the burgeoning home assistant market has seen a lot of moves recently. In the next year, that market is expected to get even larger. A recent survey from Edison Research and NPR indicated 42 percent of smart speaker owners have more than one home speaker. The report also includes other encouraging signs for smart speaker manufacturers: 70 percent of owners said they are listening to more audio at home and 65 percent of polled users said they wouldn't want to go back to not having a speaker in their homes. In the survey, parents said they were major fans of the devices.

That advice, quoted in Machine, Platform, Crowd, is well followed by Andrew McAfee and Erik Brynjolfsson in their latest business book, which tries to make sense of the "technology surge" that is bewildering so many executives. The two academic authors from Massachusetts Institute of Technology, who became the pin-up boys of the Davos crowd for their previous book on The Second Machine Age (2014), do a neat job of scanning the technological horizon and highlighting significant landmarks. This is a clear and crisply written account of machine intelligence, big data and the sharing economy. But McAfee and Brynjolfsson also wisely acknowledge the limitations of their futurology and avoid over-simplification. No one can really have much idea how the business world is going to evolve or predict the precise interplay between all these fast-changing forces.

Dr Crystal Valentine, the company's vice-president of technology strategy, told iTWire in an interview that it was still the very early days of seeing machine learning and deep learning being put to work by enterprises outside academia. Dr Valentine has a background in big data research and practice and before joining MapR, she was a professor of computer science at Amherst College. She has authored various academic publications in the areas of algorithms, high-performance computing, and computational biology and holds a patent for Extreme Virtual Memory. As a former consultant at Ab Initio Software, working with Fortune 500 companies to design and implement high-throughput, mission-critical applications and as a tech expert consulting for equity investors focused on technology, Dr Valentine has developed significant business experience in the enterprise computing industry. Dr Crystal Valentine: Machine learning encompasses a number of different algorithms for training computers to solve specific tasks, including tasks that are part of larger artificial intelligence systems.

At least since Isaac Asimov posited the Three Law of Robotics, many have wondered whether robots would ultimately help or harm humanity. Or maybe do a little of both. Humanity still has time to shape the answer to that question, and we're pleased to announce three speakers who have distinctive, grounded perspectives on how to secure a world made better (not worse) by robots. These speakers join our agenda for TechCrunch Sessions: Robotics, our first one-day event dedicated to discussing the core topics facing the robotics industry. General admission tickets are currently available for purchase though seating is very limited.

We develop a simple routine unifying the analysis of several important recently-developed stochastic optimization methods including SAGA, Finito, and stochastic dual coordinate ascent (SDCA). First, we show an intrinsic connection between stochastic optimization methods and dynamic jump systems, and propose a general jump system model for stochastic optimization methods. Our proposed model recovers SAGA, SDCA, Finito, and SAG as special cases. Then we combine jump system theory with several simple quadratic inequalities to derive sufficient conditions for convergence rate certifications of the proposed jump system model under various assumptions (with or without individual convexity, etc). The derived conditions are linear matrix inequalities (LMIs) whose sizes roughly scale with the size of the training set. We make use of the symmetry in the stochastic optimization methods and reduce these LMIs to some equivalent small LMIs whose sizes are at most 3 by 3. We solve these small LMIs to provide analytical proofs of new convergence rates for SAGA, Finito and SDCA (with or without individual convexity). We also explain why our proposed LMI fails in analyzing SAG. We reveal a key difference between SAG and other methods, and briefly discuss how to extend our LMI analysis for SAG. An advantage of our approach is that the proposed analysis can be automated for a large class of stochastic methods under various assumptions (with or without individual convexity, etc).

Large-scale datasets have played a significant role in progress of neural network and deep learning areas. YouTube-8M is such a benchmark dataset for general multi-label video classification. It was created from over 7 million YouTube videos (450,000 hours of video) and includes video labels from a vocabulary of 4716 classes (3.4 labels/video on average). It also comes with pre-extracted audio & visual features from every second of video (3.2 billion feature vectors in total). Google cloud recently released the datasets and organized 'Google Cloud & YouTube-8M Video Understanding Challenge' on Kaggle. Competitors are challenged to develop classification algorithms that assign video-level labels using the new and improved Youtube-8M V2 dataset. Inspired by the competition, we started exploration of audio understanding and classification using deep learning algorithms and ensemble methods. We built several baseline predictions according to the benchmark paper and public github tensorflow code. Furthermore, we improved global prediction accuracy (GAP) from base level 77% to 80.7% through approaches of ensemble.

We propose a simple and efficient approach to learning sparse models. Our approach consists of (1) projecting the data into a lower dimensional space, (2) learning a dense model in the lower dimensional space, and then (3) recovering the sparse model in the original space via compressive sensing. We apply this approach to Non-negative Matrix Factorization (NMF), tensor decomposition and linear classification---showing that it obtains $10\times$ compression with negligible loss in accuracy on real data, and obtains up to $5\times$ speedups. Our main theoretical contribution is to show the following result for NMF: if the original factors are sparse, then their projections are the sparsest solutions to the projected NMF problem. This explains why our method works for NMF and shows an interesting new property of random projections: they can preserve the solutions of non-convex optimization problems such as NMF.