Neurites in phase-contrast images are traditionally difficult to define by classic thresholding. Segment.ai can be trained on a small subset of hand-traced neurites to automatically detect and segment neurites from thousands of untraced datasets. Imaging dim fluorescent samples or applications that require low-level light exposure typically result in compromised image quality with poor signal-to-noise ratio. Enhance.ai can then restore details in under-exposed or dim fluorescent images, enabling researchers to gain more insights from their low-signal imaging applications. Launched earlier this year, Denoise.ai removes shot noise from resonant confocal images and can be performed in real-time.

About a year ago, I wrote that mounting AI hype would likely give way to yet another AI winter. Now, according to the panelists at "the world's leading academic AI conference" the temperature is already falling. Most recent advances in AI have come through a pair of related technologies: Deep Learning and Neural Networks. The ideas beneath these, however, are more than 70 years old. Warren McCulloch and Walter Pitts (1943) opened the subject by creating a computational model for neural networks…The first functional networks with many layers were published by Ivakhnenko and Lapa in 1965, as the Group Method of Data Handling.

The popular TV show, Shark Tank, has a familiar formula. Business owners pitch their ideas to a panel of judges known as "sharks," who have the option to invest in the company or turn the offer down. Some amazing products have launched on Shark Tank, but for every success, there are multiple failures. Many ridiculous ideas have crashed and burned -- like the Ionic Ear, Bluetooth headphones that are surgically implanted into your ears. The heartbreak comes when contestants use their pitch to highlight the sacrifices they've made -- huge investments of time and money into a product that ultimately goes nowhere.

Barely a day passes without a new scandal emerging, from questionable surveillance to racist AI algorithms. But it hasn't all been bad: while negatives get a lot of attention (and so they should – the consequences of tech can be lethal, both societally and literally), there was still plenty to get excited about. And for those working in the data profession – as analysts, scientists, and engineers, there were several important trends that really helped to define where we are now from a purely practical perspective – as well as hinting at where we might go in the future. With just a few weeks left to go of the year (and the decade!), let's look at some of the key things that defined this year in the field of data science and data engineering. TensorFlow is undoubtedly the most popular deep learning framework.

Recent observations with varied schedules and types (moving average, snapshot, or regularly spaced) can help to improve streamflow forecast but it is difficult to effectively integrate them. Based on a long short-term memory (LSTM) streamflow model, we tested different formulations in a flexible method we call data integration (DI) to integrate recently discharge measurements to improve forecast. DI accepts lagged inputs either directly or through a convolutional neural network (CNN) unit. DI can ubiquitously elevate streamflow forecast performance to unseen levels, reaching a continental-scale median Nash-Sutcliffe coefficient of 0.86. Integrating moving-average discharge, discharge from a few days ago, or even average discharge of the last calendar month could all improve daily forecast. It turned out, directly using lagged observations as inputs was comparable in performance to using the CNN unit. Importantly, we obtained valuable insights regarding hydrologic processes impacting LSTM and DI performance. Before applying DI, the original LSTM worked well in mountainous regions and snow-dominated regions, but less so in regions with low discharge volumes (due to either low precipitation or high precipitation-energy synchronicity) and large inter-annual storage variability. DI was most beneficial in regions with high flow autocorrelation: it greatly reduced baseflow bias in groundwater-dominated western basins; it also improved the peaks for basins with dynamical surface water storage, e.g., the Prairie Potholes or Great Lakes regions. However, even DI cannot help high-aridity basins with one-day flash peaks. There is much promise with a deep-learning-based forecast paradigm due to its performance, automation, efficiency, and flexibility.

When and why can a neural network be successfully trained? This article provides an overview of optimization algorithms and theory for training neural networks. First, we discuss the issue of gradient explosion/vanishing and the more general issue of undesirable spectrum, and then discuss practical solutions including careful initialization and normalization methods. Second, we review generic optimization methods used in training neural networks, such as SGD, adaptive gradient methods and distributed methods, and theoretical results for these algorithms. Third, we review existing research on the global issues of neural network training, including results on bad local minima, mode connectivity, lottery ticket hypothesis and infinite-width analysis.

Neural network compression methods have enabled deploying large models on emerging edge devices with little cost, by adapting already-trained models to the constraints of these devices. The rapid development of AI-capable edge devices with limited computation and storage requires streamlined methodologies that can efficiently satisfy the constraints of different devices. In contrast, existing methods often rely on heuristic and manual adjustments to maintain accuracy, support only coarse compression policies, or target specific device constraints that limit their applicability. We address these limitations by proposing the TOlerance-based COmpression (TOCO) framework. TOCO uses an in-depth analysis of the model, to maintain the accuracy, in an active learning system. The results of the analysis are tolerances that can be used to perform compression in a fine-grained manner. Finally, by decoupling compression from the tolerance analysis, TOCO allows flexibility to changes in the hardware.

Taking an answer and its context as input, sequence-to- sequence models have made considerable progress on question generation. However, we observe that these approaches often generate wrong question words or keywords and copy answer-irrelevant words from the input. We believe that lacking global question semantics and exploiting answer position-awareness not well are the key root causes. In this paper, we propose a neural question generation model with two concrete modules: sentence-level semantic matching and answer position inferring. Further, we enhance the initial state of the decoder by leveraging the answer-aware gated fusion mechanism. Experimental results demonstrate that our model outperforms the state-of-the-art (SOT A) models on SQuAD and MARCO datasets. Owing to its generality, our work also improves the existing models significantly.

Biomedical documents such as Electronic Health Records (EHRs) contain a large amount of information in an unstructured format. The data in EHRs is a hugely valuable resource documenting clinical narratives and decisions, but whilst the text can be easily understood by human doctors it is challenging to use in research and clinical applications. To uncover the potential of biomedical documents we need to extract and structure the information they contain. The task at hand is Named Entity Recognition and Linking (NER+L). The number of entities, ambiguity of words, overlapping and nesting make the biomedical area significantly more difficult than many others. To overcome these difficulties, we have developed the Medical Concept Annotation Tool (MedCAT), an open-source unsupervised approach to NER+L. MedCAT uses unsupervised machine learning to disambiguate entities. It was validated on MIMIC-III (a freely accessible critical care database) and MedMentions (Biomedical papers annotated with mentions from the Unified Medical Language System). In case of NER+L, the comparison with existing tools shows that MedCAT improves the previous best with only unsupervised learning (F1=0.848 vs 0.691 for disease detection; F1=0.710 vs. 0.222 for general concept detection). A qualitative analysis of the vector embeddings learnt by MedCAT shows that it captures latent medical knowledge available in EHRs (MIMIC-III). Unsupervised learning can improve the performance of large scale entity extraction, but it has some limitations when working with only a couple of entities and a small dataset. In that case options are supervised learning or active learning, both of which are supported in MedCAT via the MedCATtrainer extension. Our approach can detect and link millions of different biomedical concepts with state-of-the-art performance, whilst being lightweight, fast and easy to use.

In recent years, Graph Convolutional Networks (GCNs) and their variants have been widely utilized in learning tasks that involve graphs. These tasks include recommendation systems, node classification, among many others. In node classification problem, the input is a graph in which the edges represent the association between pairs of nodes, multi-dimensional feature vectors are associated with the nodes, and some of the nodes in the graph have known labels. The objective is to predict the labels of the nodes that are not labeled, using the nodes features, in conjunction with graph topology. While GCNs have been successfully applied to this problem, the caveats that they inherit from traditional deep learning models pose significant challenges to broad utilization of GCNs in node classification. One such caveat is that training a GCN requires a large number of labeled training instances, which is often not the case in realistic settings. To remedy this requirement, state-of-the-art methods leverage network diffusion-based approaches to propagate labels across the network before training GCNs. However, these approaches ignore the tendency of the network diffusion methods in biasing proximity with centrality, resulting in the propagation of labels to the nodes that are well-connected in the graph. To address this problem, here we present an alternate approach to extrapolating node labels in GCNs in the following three steps: (i) clustering of the network to identify communities, (ii) use of network diffusion algorithms to quantify the proximity of each node to the communities, thereby obtaining a low-dimensional topological profile for each node, (iii) comparing these topological profiles to identify nodes that are most similar to the labeled nodes.