I cover artificial intelligence and Google DeepMind. In previous roles I've written about tech policy, European startups, the gig economy, and venture capital. Previously I was a senior t...

A system under development at Purdue University uses artificial intelligence to detect cracks captured in videos of nuclear reactors and represents a future inspection technology to help reduce accidents and maintenance costs. "Regular inspection of nuclear power plant components is important to guarantee safe operations," said Mohammad R. Jahanshahi, an assistant professor in Purdue's Lyles School of Civil Engineering. "However, current practice is time-consuming, tedious, and subjective and involves human technicians reviewing inspection videos to identify cracks on reactors." Complicating the inspection process is that nuclear reactors are submerged in water to maintain cooling. Consequently, direct manual inspection of a reactor's components is not feasible due to high temperatures and radiation hazards.

We seek ever more data for a good reason: it's the commodity that fuels digital innovation. However, turning those huge data collections into actionable insight remains a difficult proposition. Organizations that find solutions to formidable data challenges will be better positioned to economically benefit from the fruits of digital innovation. The big idea behind big data analytics is fairly clear-cut: Find interesting patterns hidden in large amounts of data, train machine learning models to spot those patterns, and implement those models into production to automatically act upon them. However, the reality of putting that basic recipe into production is a lot harder than it looks.

We seek ever more data for a good reason: it's the commodity that fuels digital innovation. However, turning those huge data collections into actionable insight remains a difficult proposition. Organizations that find solutions to formidable data challenges will be better positioned to economically benefit from the fruits of digital innovation. The big idea behind big data analytics is fairly clear-cut: Find interesting patterns hidden in large amounts of data, train machine learning models to spot those patterns, and implement those models into production to automatically act upon them. However, the reality of putting that basic recipe into production is a lot harder than it looks.

Deep learning is a buzzword that has been hyped by the business and technical press for years, often with relatively meager results that failed to live up to expectations. But over the past 18 months, according to a new report from Tractica, the true power of deep learning has been realized, thanks to advances in hardware and algorithms that use pattern recognition applied in a continuous learning loop, enabling them to train themselves to perform tasks without requiring explicit programming code. The sheer power of deep learning, however, is likely to lead to the development of more powerful and disruptive applications of tomorrow, such as driverless cars, personalized education, and preventative healthcare. Tractica forecasts that, with this expanding set of applications, the worldwide deep learning software market will grow from $3 billion in 2017 to $67.2 billion by 2025. "Deep learning has been a key point of focus for many companies, given its potential to transform entire industries," says principal analyst Keith Kirkpatrick.

Community detection refers to the task of discovering groups of vertices sharing similar properties or functions so as to understand the network data. With the recent development of deep learning, graph representation learning techniques are also utilized for community detection. However, the communities can only be inferred by applying clustering algorithms based on learned vertex embeddings. These general cluster algorithms like K-means and Gaussian Mixture Model cannot output much overlapped communities, which have been proved to be very common in many real-world networks. In this paper, we propose CommunityGAN, a novel community detection framework that jointly solves overlapping community detection and graph representation learning. First, unlike the embedding of conventional graph representation learning algorithms where the vector entry values have no specific meanings, the embedding of CommunityGAN indicates the membership strength of vertices to communities. Second, a specifically designed Generative Adversarial Net (GAN) is adopted to optimize such embedding. Through the minimax competition between the motif-level generator and discriminator, both of them can alternatively and iteratively boost their performance and finally output a better community structure. Extensive experiments on synthetic data and real-world tasks demonstrate that CommunityGAN achieves substantial community detection performance gains over the state-of-the-art methods.

Recognizing pedestrian attributes is an important task in computer vision community due to it plays an important role in video surveillance. Many algorithms has been proposed to handle this task. The goal of this paper is to review existing works using traditional methods or based on deep learning networks. Firstly, we introduce the background of pedestrian attributes recognition (PAR, for short), including the fundamental concepts of pedestrian attributes and corresponding challenges. Secondly, we introduce existing benchmarks, including popular datasets and evaluation criterion. Thirdly, we analyse the concept of multi-task learning and multi-label learning, and also explain the relations between these two learning algorithms and pedestrian attribute recognition. We also review some popular network architectures which have widely applied in the deep learning community. Fourthly, we analyse popular solutions for this task, such as attributes group, part-based, \emph{etc}. Fifthly, we shown some applications which takes pedestrian attributes into consideration and achieve better performance. Finally, we summarized this paper and give several possible research directions for pedestrian attributes recognition. The project page of this paper can be found from the following website: \url{https://sites.google.com/view/ahu-pedestrianattributes/}.

Rapid identification of bacteria is essential to prevent the spread of infectious disease, help combat antimicrobial resistance, and improve patient outcomes. Raman optical spectroscopy promises to combine bacterial detection, identification, and antibiotic susceptibility testing in a single step. However, achieving clinically relevant speeds and accuracies remains challenging due to the weak Raman signal from bacterial cells and the large number of bacterial species and phenotypes. By amassing the largest known dataset of bacterial Raman spectra, we are able to apply state-of-the-art deep learning approaches to identify 30 of the most common bacterial pathogens from noisy Raman spectra, achieving antibiotic treatment identification accuracies of 99.0$\pm$0.1%. This novel approach distinguishes between methicillin-resistant and -susceptible isolates of Staphylococcus aureus (MRSA and MSSA) as well as a pair of isogenic MRSA and MSSA that are genetically identical apart from deletion of the mecA resistance gene, indicating the potential for culture-free detection of antibiotic resistance. Results from initial clinical validation are promising: using just 10 bacterial spectra from each of 25 isolates, we achieve 99.0$\pm$1.9% species identification accuracy. Our combined Raman-deep learning system represents an important proof-of-concept for rapid, culture-free identification of bacterial isolates and antibiotic resistance and could be readily extended for diagnostics on blood, urine, and sputum.

This paper presents a new conditional GAN (named convex relaxing CGAN or crCGAN) to replicate the conventional constrained topology optimization algorithms in an extremely effective and efficient process. The proposed crCGAN consists of a generator and a discriminator, both of which are deep convolutional neural networks (CNN) and the topology design constraint can be conditionally set to both the generator and discriminator. In order to improve the training efficiency and accuracy due to the dependency between the training images and the condition, a variety of crCGAN formulation are introduced to relax the non-convex design space. These new formulations were evaluated and validated via a series of comprehensive experiments. Moreover, a minibatch discrimination technique was introduced in the crCGAN training process to stabilize the convergence and avoid the mode collapse problems. Additional verifications were conducted using the state-of-the-art MNIST digits and CIFAR-10 images conditioned by class labels. The experimental evaluations clearly reveal that the new objective formulation with the minibatch discrimination training provides not only the accuracy but also the consistency of the designs.

Modelling long-term dependencies is a challenge for recurrent neural networks. This is primarily due to the fact that gradients vanish during training, as the sequence length increases. Gradients can be attenuated by transition operators and are attenuated or dropped by activation functions. Canonical architectures like LSTM alleviate this issue by skipping information through a memory mechanism. We propose a new recurrent architecture (Non-saturating Recurrent Unit; NRU) that relies on a memory mechanism but forgoes both saturating activation functions and saturating gates, in order to further alleviate vanishing gradients. In a series of synthetic and real world tasks, we demonstrate that the proposed model is the only model that performs among the top 2 models across all tasks with and without long-term dependencies, when compared against a range of other architectures.