This paper considers the problem of inferring image labels for which only a few labelled examples are available at training time. This setup is often referred to as low-shot learning in the literature, where a standard approach is to re-train the last few layers of a convolutional neural network learned on separate classes. We consider a semi-supervised setting in which we exploit a large collection of images to support label propagation. This is made possible by leveraging the recent advances on large-scale similarity graph construction. We show that despite its conceptual simplicity, scaling up label propagation to up hundred millions of images leads to state of the art accuracy in the low-shot learning regime.

We present a method for synthesizing a frontal, neutralexpression image of a person's face given an input face photograph. This is achieved by learning to generate facial landmarks and textures from features extracted from a facial-recognition network. Unlike previous generative approaches, our encoding feature vector is largely invariant to lighting, pose, and facial expression. Exploiting this invariance, we train our decoder network using only frontal, neutral-expression photographs. Since these photographs are well aligned, we can decompose them into a sparse set of landmark points and aligned texture maps. The decoder then predicts landmarks and textures independently and combines them using a differentiable image warping operation. The resulting images can be used for a number of applications, such as analyzing facial attributes, exposure and white balance adjustment, or creating a 3-D avatar.

Artificial intelligence systems are starting to think "like humans" rather than just calculating potential options, but might their full exploitation trigger some liability risks? As anticipated, IoTItaly, the Italian Association on the Internet of Things of which I am one of the founders, ran an event in collaboration with STMicroelectronics named "Creativity and technology at the time of Industry 4.0" on 30 May 2017. I found fascinating the video below that tries to explain Google's DeepMind system. As mentioned in the video, the "symbolic" event which is considered the moment when machines started to be "intuitive" is the victory of the AlphaGo artificial intelligence system against a master of the ancient Chinese game Go. DeepMind is the evolution of such approach.

Would you like to take a course on Keras and deep learning in Python? Consider taking DataCamp's Deep Learning in Python course! Also, don't miss our Keras cheat sheet, which shows you the six steps that you need to go through to build neural networks in Python with code examples! Before going deeper into Keras and how you can use it to get started with deep learning in Python, you should probably know a thing or two about neural networks. As you briefly read in the previous section, neural networks found their inspiration and biology, where the term "neural network" can also be used for neurons.

As an Indian guy living in the US, I have a constant flow of money from home to me and vice versa. If the USD is stronger in the market, then the Indian rupee (INR) goes down, hence, a person from India buys a dollar for more rupees. If the dollar is weaker, you spend less rupees to buy the same dollar. If one can predict how much a dollar will cost tomorrow, then this can guide one's decision making and can be very important in minimizing risks and maximizing returns. Looking at the strengths of a neural network, especially a recurrent neural network, I came up with the idea of predicting the exchange rate between the USD and the INR.

Last week I was fortunate enough to have attended the RE•WORK Deep Learning Summit Montreal (October 10 & 11), and was able to take in a number of quality talks and meet with other attendees. The conference was split into 2 tracks -- Research Advancements and Business Applications -- and featured a wide array of top neural networks researchers and academics, as well as business leaders. An interesting mix of both industry and academic, RE•WORK did more than enough to prove their professionalism and attention to detail, and this is without mentioning the calibre of speakers they secured for the event. What follows is a summary of some of my favorite talks from the conference, with this selection revolving around the visual reasoning & computer vision blocks which started the conference off. A full listing of the speakers and schedule can be found here. Aaron Courville, of the University of Montreal, kicked off the research developments track of the conference with his talk titled Visual Reasoning via Feature-wise Linear Modulation.

In this step-by-step Keras tutorial, you'll learn how to build a convolutional neural network in Python! In fact, we'll be training a classifier for handwritten digits that boasts over 99% accuracy on the famous MNIST dataset. Before we begin, we should note that this guide is geared toward beginners who are interested in applied deep learning. Our goal is to introduce you to one of the most popular and powerful libraries for building neural networks in Python. That means we'll brush over much of the theory and math, but we'll also point you to great resources for learning those.

Deep learning has been experiencing a true renaissance especially over the last decade, and it uses multi-layered artificial neural networks for automated analysis of data. Deep learning is one of the most exciting forms of machine learning that is behind several recent leapfrog advances in technology including for example real-time speech recognition and translation as well image/video labeling and captioning, among many others. Especially in image analysis, deep learning shows significant promise for automated search and labeling of features of interest, such as abnormal regions in a medical image. Now, UCLA researchers have demonstrated a new use for deep learning – this time to reconstruct a hologram and form a microscopic image of an object. In a recent article that is published in Light: Science & Applications, a journal of the Springer Nature, UCLA researchers have demonstrated that a neural network can learn to perform phase recovery and holographic image reconstruction after appropriate training.

Google's AI subsidiary DeepMind is getting serious about ethics. The UK-based company, which Google bought in 2014, today announced the formation of a new research group dedicated to the thorniest issues in artificial intelligence. These include the problems of managing AI bias; the coming economic impact of automation; and the need to ensure that any intelligent systems we develop share our ethical and moral values. DeepMind Ethics & Society (or DMES, as the new team has been christened) will publish research on these topics and others starting early 2018. The group has eight full-time staffers at the moment, but DeepMind wants to grow this to around 25 in a year's time.

New AI technologies like machine learning and deep learning are fitting ever more snugly into the shifting enterprise landscape. Deep learning in particular is being adopted by an increasing number of enterprises for expanded insights and with the aim to better serving their clients. Thanks to more powerful systems and graphics processing units (GPUs), we are able to train complex AI models that enable these insights. IBM has long been one of the leaders in analytics and over the last year or two introduced two key new products, Data Science Experience and IBM PowerAI, designed to enable enterprises to more easily start using advanced AI technologies. Today we're unveiling that we are bringing these two key software tools for data scientists together.