Inside Big Data May 7, 2018 In this recurring monthly feature, Inside Big Data filters recent research papers appearing on the arXiv.org preprint server for compelling subjects relating to AI, machine learning and deep learning – from disciplines including statistics, mathematics and computer science – and provide you with a useful “best of” list for the past month… read more.
Tag Archives: AI
Artificial intelligence helps soldiers learn many times faster in combat
Eurekalert April 27, 2018 Stochastic Gradient Descent (SGD) is widely used for Collaborative Filtering, a well-known machine learning technique for recommender systems. A team of researchers in the US (ARL, University of Southern California) has developed an FPGA-based accelerator, FASTCF, to accelerate the SGD-based CF algorithm consisting of parallel, pipelined processing units which concurrently process distinct user ratings by accessing a shared on-chip buffer. Compared with non-optimized baseline designs, the hierarchical partitioning approach they used results in up to 60x data dependency reduction, 4.2x bank conflict reduction, and 15.4x speedup… read more. TECHNICAL ARTICLE
Image Inpainting for Irregular Holes Using Partial Convolutions
Arxiv April 20, 2018 Existing deep learning-based image inpainting methods often lead to artifacts such as color discrepancy and blurriness. Researchers in the US (NVIDIA Corporation) propose the use of partial convolutions, where the convolution is masked and renormalized to be conditioned on only valid pixels. They include a mechanism to automatically generate an updated mask for the next layer as part of the forward pass. They have demonstrated that their model outperforms other methods for irregular masks. They have shown qualitative and quantitative comparisons with other methods to validate their approach… read more. Open Access TECHNICAL ARTICLE
Best of arXiv.org for AI, Machine Learning, and Deep Learning – February 2018
Inside Big data March 16, 2018 The articles listed in here represent a fraction of all articles appearing on the preprint server. A brief overview of each paper and a link to the paper are provided… read more.
China versus USA in AI potential
Next Big Future March 19, 2018 According to Oxford and the Future of Humanity report on China’s AI plans China is still far behind on hardware but ahead in mobile and data and lagging in algorithms and commercial AI companies. China has relied on imports and acquisitions to boost the most immediately relevant aspects of AI hardware. As this strategy has come under more scrutiny by the U.S. and EU, China is promoting national champions in its domestic chip-making industry and making long-term bets on powerful supercomputing facilities… read more.
Fractal AI: A fragile theory of intelligence
ArXiv March 13, 2018 Fractal AI is a theory for general artificial intelligence. It allows to derive new mathematical tools that constitute the foundations for a new kind of stochastic calculus. Among other things, Fractal AI makes it possible to generate a huge database of top performing examples with very little amount of computation required, transforming Reinforcement Learning into a supervised problem. The new techniques presented here have direct applications to other areas such as: Non-equilibrium thermodynamics, chemistry, quantum physics, economics, information theory, and non-linear control theory… read more. Open Access TECHNICAL ARTICLE
In five years quantum computing will be mainstream
Next Big Future March 19, 2018 IBM Researchers are already reaching major quantum chemistry milestones, having recently used a quantum computer to successfully simulate atomic bonding in beryllium hydride (BeH2), the most complex molecule ever simulated by a quantum computer. In the future quantum computers will continue to address problems with ever-greater complexity, eventually catching up to and surpassing what we can do with classical machines alone… read more.
Why even a moth’s brain is smarter than an AI
MIT Technology Review February 19, 2018 Some critical machine-learning mechanisms have no analogue in the natural world, where learning seems to occur in a different way. Researchers at the University of Washington have created an artificial neural network that mimics the structure and behavior of the olfactory learning system in Manduca sexta moths. Their model can robustly learn new odors, and their simulations of integrate-and-fire neurons match the statistical features of in vivo firing rate data. This work that could have significant implications for the design of synthetic neural networks that need to learn quickly…read more. Open Access TECHNICAL ARTICLE