AI experts at CognitionX and Peltarion release new report on where the value in Deep Learning (DL) lies, and where the trend for Deep Learning is moving, based on insight across industries from AI thought-leaders in Europe. Peltarion, leading AI innovator and creator of an operational deep learning platform, and AI Knowledge Network CognitionX, organiser of the CogX festival of AI and emerging technology, today released a new study based on research and interviews with other AI industry leaders across Europe such as Amazon, Google, DeepMind, and JP Morgan. The report, "Deep Learning: Opportunities and Best Practice", provides insight that deep learning is overtaking more classic Machine learning methods. However, several challenges remain; cost, complexity, and skills are yet to be solved to enable market growth. The study is intended to serve as a primer for those with shallow knowledge about deep learning, and a guide for those with more experience.

With plenty of mics and cameras at disposal, AI has gotten good at'seeing' and'listening.' But one human sense it hasn't got around much is smell. Now, researchers at Google are trying to develop a neural network that helps an AI identify the smell characteristics of a molecule. The company said identifying smell is a multi-label classification problem, meaning a substance can have multiple smell characteristics. For instance, Vanillin, a substance often used to create an artificial vanilla flavor, has multiple smell descriptors such as sweet, vanilla, and chocolate, with some characteristics stronger than others. So, to identify the smell profile of a molecule researchers used a graph neural networks (GNNs), a deep learning model that takes graphs as inputs.

For all the shortcomings of deep learning etc: these news are going to be mainstream soon.

Last year we were amazed by the level of dexterity achieved by OpenAI's Dactyl system which was able to learn how to manipulate a cube block to display any commanded side/face.If you missed that article, read about it here. OpenAI then set themselves a harder task of teaching the robotic hand to solve a Rubik's cube. Quite a daunting task made no easier by the fact that it would use one hand which most humans would find it hard to do. OpenAI harnessed the power of neural networks which are trained entirely in simulation. However, one of the main challenges faced was to make the simulations as realistic as possible because physical factors like friction, elasticity etc. are very hard to model.

This is a Part 2 of my Machine Learning in iOS tutorials, check Part 1 first. You may have read my previous article about Machine Learning in iOS: IBM Watson and CoreML. So you know that Machine Learning can be intimidating with lots of concepts and frameworks to learn, not to mention that we need to understand algorithms in Python. Talking about image labelling, you might have a bunch of images and you want to train the machine to understand and classify them. Training your own custom deep learning models can be challenging.

Liver alignment between series/exams is challenged by dynamic morphology or variability in patient positioning or motion. Image registration can improve image interpretation and lesion co-localization. We assessed the performance of a convolutional neural network algorithm to register cross-sectional liver imaging series and compared its performance to manual image registration. Three hundred fourteen patients, including internal and external datasets, who underwent gadoxetate disodium-enhanced magnetic resonance imaging for clinical care from 2011 to 2018, were retrospectively selected. Automated registration was applied to all 2,663 within-patient series pairs derived from these datasets.

We've all seen those sci-fi movies where the government can use a small device to read a person's mind, exposing their innermost thoughts. Usually, those films are set in the distant future with space aliens flying around. While we haven't found any aliens yet, mind-reading technology might not be that far off. Thanks to a recent breakthrough, computers have gotten a step closer to being able to read our thoughts. Using deep learning and a speech synthesizer, a team at Columbia University was able to translate brain activity into words.

We examine Generative Adversarial Networks (GANs) through the lens of deep Energy Based Models (EBMs), with the goal of exploiting the density model that follows from this formulation. In contrast to a traditional view where the discriminator learns a constant function when reaching convergence, here we show that it can provide useful information for downstream tasks, e.g., feature extraction for classification. To be concrete, in the EBM formulation, the discriminator learns an unnormalized density function (i.e., the negative energy term) that characterizes the data manifold. We propose to evaluate both the generator and the discriminator by deriving corresponding Fisher Score and Fisher Information from the EBM. We show that by assuming that the generated examples form an estimate of the learned density, both the Fisher Information and the normalized Fisher Vectors are easy to compute. We also show that we are able to derive a distance metric between examples and between sets of examples. We conduct experiments showing that the GAN-induced Fisher Vectors demonstrate competitive performance as unsupervised feature extractors for classification and perceptual similarity tasks. Code is available at \url{https://github.com/apple/ml-afv}.

Recent work by Brock et al. (2018) suggests that Generative Adversarial Networks (GANs) benefit disproportionately from large mini-batch sizes. Unfortunately, using large batches is slow and expensive on conventional hardware. Thus, it would be nice if we could generate batches that were effectively large though actually small. In this work, we propose a method to do this, inspired by the use of Coreset-selection in active learning. When training a GAN, we draw a large batch of samples from the prior and then compress that batch using Coreset-selection. To create effectively large batches of 'real' images, we create a cached dataset of Inception activations of each training image, randomly project them down to a smaller dimension, and then use Coreset-selection on those projected activations at training time. We conduct experiments showing that this technique substantially reduces training time and memory usage for modern GAN variants, that it reduces the fraction of dropped modes in a synthetic dataset, and that it allows GANs to reach a new state of the art in anomaly detection.

ABSTRACT In this paper, we address customer review understanding problems by using supervised machine learning approaches, in order to achieve a fully automatic review aspects categorisation and sentiment analysis. In general, such supervised learning algorithms require domain-specific expert knowledge for generating high quality labeled training data, and the cost of labeling can be very high. To achieve an in-production customer review machine learning enabled analysis tool with only a limited amount of data and within a reasonable training data collection time, we propose to use pre-trained language representation to boost model performance and active learning framework for accelerating the iterative training process. The results show that with integration of both components, the fully automatic review analysis can be achieved at a much faster pace. Index T erms -- deep neural networks, natural language processing, embedding, active learning, sentiment analysis, multi-aspect classification 1. INTRODUCTION Natural language processing has gain continuously attention in recent years, not only for academe research purposes but also for a real-world use case in various industrial sectors.