Evolutionary data mining and applications: A revision on the most cited papers from the last 10?years (2007–2017)

The ability of evolutionary algorithms (EAs) to manage a set of solutions, even attending multiple objectives, as well as their ability to optimize any kinds of values, allows them to fit very well some parts of the data-mining (DM) problems, whose native learning techniques usually associated with the inherent DM problem are not able to solve. Therefore, EAs are widely applied to complement or even replace the classical DM learning approaches. This application of EAs to the DM process is usually named evolutionary data mining (EDM). This contribution aims at showing a glimpse of the EDM field current state by focusing on the most cited papers published in the last 10?years. A descriptive analysis of the papers together with a bibliographic study is performed in order to differentiate past and current trends and to easily focus on significant further developments. Results show that, in the case of the most cited studied papers, the use of EAs on DM tasks is mainly focused on enhancing the classical learning techniques, thus completely replacing them only when it is directly motivated by the nature of problem. The bibliographic analysis is also showing that even though EAs were the main techniques used for EDM, the emergent evolutionary computation algorithms (swarm intelligence, etc.) are becoming nowadays the most cited and used ones. Based on all these facts, some potential further directions are also discussed.


CDO or CAO?

If you have committed to data and analytics as strategically important to your business, should you have a Chief Data Officer (CDO) or a Chief Analytics Officer (CAO)? What’s the difference and what’s the trend?


Interactive Segmentation with Convolutional Neural

Recently animated stickers have increased in popularity due to their massive use in messaging applications or memes. Still, with existing tools, generating animated stickers is extremely challenging and time-consuming, making the task practically infeasible for non-experts. Removing the background of an arbitrary video (no green screen) is a menial task that involves manually segmenting the object in each frame of a video.


Getting Started with TensorFlow: A Machine Learning Tutorial

TensorFlow is an open source software library created by Google that is used to implement machine learning and deep learning systems. These two names contain a series of powerful algorithms that share a common challenge—to allow a computer to learn how to automatically spot complex patterns and/or to make best possible decisions.


The artificial intelligence computing stack

A gigantic shift in computing is about to dawn upon us, one that is as significant as only two other moments in computing history. First came the “desktop era” of computing, powered by central processing units (CPUs), followed by the “mobile era” of computing, powered by more power-efficient mobile processors. Now, there is a new computing stack that is moving all of software with it, fueled by artificial intelligence (AI) and chips specifically designed to accommodate its grueling computations. In the past decade, the computational demands of AI put a strain on CPUs, unable to shake off physical limits in clock speed and heat dissipation. Luckily, the computations that AI requires only need linear algebra operations, the same linear algebra you learned about in high school mathematics. It turns out the best hardware for AI speaks linear algebra natively, and graphics processing units (GPUs) are pretty good at that, so we used GPUs to make great strides in AI.


Distributed TensorFlow

On June 8, 2017, the age of distributed deep learning began. On that day, Facebook released a paper showing the methods they used to reduce the training time for a convolutional neural network (RESNET-50 on ImageNet) from two weeks to one hour, using 256 GPUs spread over 32 servers. In software, they introduced a technique to train convolutional neural networks (ConvNets) with very large mini-batch sizes: make the learning rate proportional to the mini-batch size. This means anyone can now scale out distributed training to 100s of GPUs using TensorFlow. But that’s not the only advantage of distributed TensorFlow: you can also massively reduce your experimentation time by running many experiments in parallel on many GPUs. This reduces the time required to find good hyperparameters for your neural network.


Apache MXNet in the Wolfram Language

The Wolfram Language is a high-level, functional programming language. It’s the language behind Mathematica, but Wolfram Cloud and Wolfram Desktop are other products in which you can use it. The language itself includes a built-in neural net framework, which is currently implemented using MXNet as a back end.
Advertisements