PyData Amsterdam 2017 Deep learning has been widely influential in academic research and also recently finding its way into the industry. This talk explains how we utilize deep learning techniques at the Booking.com Use cases go beyond image analysis towards solving a variety of regression and classification problems. Deep learning has been widely influential in academic research and also recently finding its way into the industry. This talk explains how we utilize deep learning techniques at the Booking.com

I recently stumbled across an old Data Science Stack Exchange answer of mine on the topic of the "Best Python library for neural networks", and it struck me how much the Python deep learning ecosystem has evolved over the course of the past 2.5 years. The library I recommended in July 2014, pylearn2, is no longer actively developed or maintained, but a whole host of deep learning libraries have sprung up to take its place. Each has its own strengths and weaknesses. We've used most of the technologies on this list in production or development at indico, but for the few that we haven't, I'll pull from the experiences of others to help give a clear, comprehensive picture of the Python deep learning ecosystem of 2017. In particular, we'll be looking at: Theano is a Python library that allows you to define, optimize, and evaluate mathematical expressions involving multi-dimensional arrays efficiently.

Artificial intelligence is affecting everything from automobiles to health care to home automation and even sports. It's also going to have a measurable impact on software development, with developers becoming more like data scientists, an AI official with Nvidia believes. AI and deep learning will mean changes in how software is written, said Jim McHugh, vice president and general manager for Nvidia's DGX-1 supercomputer, which is used in deep learning and accelerated analytics. The long-standing paradigm of developers spending months simply writing features will change, he explained. With the advent of AI, data is incorporated to create the insight for software.

Deep discriminative classifiers perform remarkably well on problems with a lot of labeled data. So-called deep generative models tend to excel when labeled training data is scarce. Can we do a hybrid, combining the best of both worlds? In this post I outline a hybrid generative-discriminative deep model loosely based on the importance weighted autoencoder (Burda et al., 2015). Don't miss the pretty pictures.

Aidence, an Amsterdam-based start-up applying Artificial Intelligence to the interpretation of medical images, today announced its raise of €2.25M in seed funding from notable investors Northzone, HenQ, Health Innovations, and the medical specialists of the Haaglanden hospital group. The investment will be used to strengthen its sales and technical teams and expand international reach. Aidence is improving healthcare using Computer-Aided Diagnostics, with a first application in lung cancer. Aidence's software enables faster, cheaper, and more accurate diagnoses of X-ray, MRI and CT images. The key enabling technology is Deep Learning, a revolutionary type of Artificial Intelligence that is capable of analysing medical images with human-level accuracy.

There is plenty of interest in recurrent neural networks (RNNs) for the generation of data that is meaningful, and even fascinating to humans. Popular examples generate everything from credible (but fabricated) passages from Shakespeare, incredible (but highly likely) fake-news clickbait, to completely simulated handwritten sentences that shadow the style of the original writer. Such compelling examples demonstrate the power of recurrent neural networks for modelling human generated data, and recreating completely new data from those models. They can be understood by anybody, humanising the world of "AI". Inspired, Consected, sponsored research into the use of machine learning to generate new speech by modelling human speech audio, without any intermediate text or word representations.

The goal of this article is to provide an overview of frameworks relevant to Machine Learning and Artificial Intelligence released by large corporations. We focus not just on pure Machine Learning and AI tools but also include some Big Data frameworks which provide value in making Machine Learning and AI available at scale. While these releases do have very strategic business reasons, there is no doubt that the trend of open-sourcing internal tools is adding value and making Machine Learning and AI more accessible. Over the past 2-3 years a large number of frameworks have been open-sourced. Companies may wish to establish standards, showcase their advanced level of research, attract talent or leverage the power of a community when open-sourcing tools. Whatever the reasons may be for open-sourcing tools, large organizations tend to have extensive resources which they use to build their internal tools. For businesses interested in exploring Data Science it only makes sense to evaluate whether any effort that has already gone into building these frameworks can be leveraged. We provide a summary of released tools, but not a comparison of the individual frameworks. Especially when it comes to Deep Learning, entire communities have formed around tools, and with that very dedicated fans and opponents. While we avoid such discussions, we provide our own observations and conclude the article with some generic guidelines for evaluating frameworks for business use.

That's an interesting question, and I try to answer this is a very general way. The tl;dr version of this is: Deep learning is essentially a set of techniques that help we to parameterize deep neural network structures, neural networks with many, many layers and parameters. And if we are interested, a more concrete example: Let's start with multi-layer perceptrons (MLPs)... On a tangent: The term "perceptron" in MLPs may be a bit confusing since we don't really want only linear neurons in our network. Using MLPs, we want to learn complex functions to solve non-linear problems. Thus, our network is conventionally composed of one or multiple "hidden" layers that connect the input and output layer.

Each one is a repository in its own, and they cover topics such as time series, regression, outliers, clustering, correlation, Hadoop, deep learning, Python, IoT, data sets, cheat sheets, infographics, and more (AI coming soon.)

Deep learning and machine learning both offer ways to train models and classify data. This video compares the two, and it offers ways to help you decide which one to use. Let's start by discussing the classic example of distinguishing cats from dogs. Now, in this picture, do you see a cat or a dog? How were you able to answer that?