In many real-world machine learning applications, unlabeled data can be easily obtained, but it is very time-consuming and/or expensive to label them. So, it is desirable to be able to select the optimal samples to label, so that a good machine learning model can be trained from a minimum amount of labeled data. Active learning (AL) has been widely used for this purpose. However, most existing AL approaches are supervised: they train an initial model from a small amount of labeled samples, query new samples based on the model, and then update the model iteratively. Few of them have considered the completely unsupervised AL problem, i.e., starting from zero, how to optimally select the very first few samples to label, without knowing any label information at all. This problem is very challenging, as no label information can be utilized. This paper studies unsupervised pool-based AL for linear regression problems. We propose a novel AL approach that considers simultaneously the informativeness, representativeness, and diversity, three essential criteria in AL. Extensive experiments on 14 datasets from various application domains, using three different linear regression models (ridge regression, LASSO, and linear support vector regression), demonstrated the effectiveness of our proposed approach.

Epilepsy affects nearly 1% of the global population, of which two thirds can be treated by anti-epileptic drugs and a much lower percentage by surgery. Diagnostic procedures for epilepsy and monitoring are highly specialized and labour-intensive. The accuracy of the diagnosis is also complicated by overlapping medical symptoms, varying levels of experience and inter-observer variability among clinical professions. This paper proposes a novel hybrid bilinear deep learning network with an application in the clinical procedures of epilepsy classification diagnosis, where the use of surface electroencephalogram (sEEG) and audiovisual monitoring is standard practice. Hybrid bilinear models based on two types of feature extractors, namely Convolutional Neural Networks (CNNs) and Recurrent Neural Networks (RNNs), are trained using Short-Time Fourier Transform (STFT) of one-second sEEG. In the proposed hybrid models, CNNs extract spatio-temporal patterns, while RNNs focus on the characteristics of temporal dynamics in relatively longer intervals given the same input data. Second-order features, based on interactions between these spatio-temporal features are further explored by bilinear pooling and used for epilepsy classification. Our proposed methods obtain an F1-score of 97.4% on the Temple University Hospital Seizure Corpus and 97.2% on the EPILEPSIAE dataset, comparing favourably to existing benchmarks for sEEG-based seizure type classification. The open-source implementation of this study is available at https://github.com/NeuroSyd/Epileptic-Seizure-Classification

Learning rates in stochastic neural network training are currently determined a priori to training, using expensive manual or automated iterative tuning. This study proposes gradient-only line searches to resolve the learning rate for neural network training algorithms. Stochastic sub-sampling during training decreases computational cost and allows the optimization algorithms to progress over local minima. However, it also results in discontinuous cost functions. Minimization line searches are not effective in this context, as they use a vanishing derivative (first order optimality condition), which often do not exist in a discontinuous cost function and therefore converge to discontinuities as opposed to minima from the data trends. Instead, we base candidate solutions along a search direction purely on gradient information, in particular by a directional derivative sign change from negative to positive (a Non-negative Associative Gradient Projection Point (NN- GPP)). Only considering a sign change from negative to positive always indicates a minimum, thus NN-GPPs contain second order information. Conversely, a vanishing gradient is purely a first order condition, which may indicate a minimum, maximum or saddle point. This insight allows the learning rate of an algorithm to be reliably resolved as the step size along a search direction, increasing convergence performance and eliminating an otherwise expensive hyperparameter.

The fruit fly Drosophila's olfactory circuit has inspired a new locality sensitive hashing (LSH) algorithm, FlyHash. In contrast with classical LSH algorithms that produce low dimensional hash codes, FlyHash produces sparse high-dimensional hash codes and has also been shown to have superior empirical performance compared to classical LSH algorithms in similarity search. However, FlyHash uses random projections and cannot learn from data. Building on inspiration from FlyHash and the ubiquity of sparse expansive representations in neurobiology, our work proposes a novel hashing algorithm BioHash that produces sparse high dimensional hash codes in a data-driven manner. We show that BioHash outperforms previously published benchmarks for various hashing methods. Since our learning algorithm is based on a local and biologically plausible synaptic plasticity rule, our work provides evidence for the proposal that LSH might be a computational reason for the abundance of sparse expansive motifs in a variety of biological systems. We also propose a convolutional variant BioConvHash that further improves performance. From the perspective of computer science, BioHash and BioConvHash are fast, scalable and yield compressed binary representations that are useful for similarity search.

Tel-Aviv based start-up Aidoc, a leading provider of Artificial Intelligence solutions for radiologists, received US Food and Drug Administration (FDA) clearance for its AI solution that spots strokes (Large-Vessel Occlusion) in the brain during head CTA scans.An LVO is the blockage of vessels in the brain, and according to Ariella Shoham, Aidoc's vice president of marketing, the AI technology "uses deep learning to automatically look at every head CT before a patient has even left the imaging room. "It investigates the images to see if they show blocked blood vessels in the brain or bleeding (intracranial hemorrhages)," she explained. "If one of these time-critical conditions is found, Aidoc re-prioritizes the worklists of radiologists so that the urgent scan is looked at immediately and the patient can be treated quickly."Shoham said that Aidoc already received FDA clearances to identify and flag pulmonary embolism (blockages in the lungs) and cervical spine fractures (broken neck). "Other Aidoc solutions currently in clinical testing include identifying air in the abdomen," she continued. "Altogether, Aidoc is targeting the most common critical life-threatening conditions that make up 80% of all urgent cases on CT scans.

Modern board games are a rich source of entertainment for many people, but also contain interesting and challenging structures for game playing research and implementing game playing agents. This paper studies the game Patchwork, a two player strategy game using polyomino tile drafting and placement. The core polyomino placement mechanic is implemented in a constraint model using regular constraints, extending and improving the model in (Lagerkvist, Pesant, 2008) with: explicit rotation handling; optional placements; and new constraints for resource usage. Crucial for implementing good game playing agents is to have great heuristics for guiding the search when faced with large branching factors. This paper divides placing tiles into two parts: a policy used for placing parts and an evaluation used to select among different placements. Policies are designed based on classical packing literature as well as common standard constraint programming heuristics. For evaluation, global propagation guided regret is introduced, choosing placements based on not ruling out later placements. Extensive evaluations are performed, showing the importance of using a good evaluation and that the proposed global propagation guided regret is a very effective guide.

Relation Extraction (RE), the task of detecting and characterizing semantic relations between entities in text, has gained much importance in the last two decades, mainly in the biomedical domain. Many papers have been published on Relation Extraction using supervised machine learning techniques. Most of these techniques rely on statistical methods, such as feature-based and tree-kernels-based methods. Such statistical learning techniques are usually based on a propositional hypothesis space for representing examples, i.e., they employ an attribute-value representation of features. This kind of representation has some drawbacks, particularly in the extraction of complex relations which demand more contextual information about the involving instances, i.e., it is not able to effectively capture structural information from parse trees without loss of information. In this work, we present OntoILPER, a logic-based relational learning approach to Relation Extraction that uses Inductive Logic Programming for generating extraction models in the form of symbolic extraction rules. OntoILPER takes profit of a rich relational representation of examples, which can alleviate the aforementioned drawbacks. The proposed relational approach seems to be more suitable for Relation Extraction than statistical ones for several reasons that we argue. Moreover, OntoILPER uses a domain ontology that guides the background knowledge generation process and is used for storing the extracted relation instances. The induced extraction rules were evaluated on three protein-protein interaction datasets from the biomedical domain. The performance of OntoILPER extraction models was compared with other state-of-the-art RE systems. The encouraging results seem to demonstrate the effectiveness of the proposed solution.

Many people may be familiar with the frustration of calling up their smartphone's speech-to-text function to dictate an email, only to find that it won't work because the phone isn't connected to the internet. Now, a new generation of edge artificial intelligence (AI) chips is set to reduce those frustrations by bringing the AI to the device.1 We predict that in 2020, more than 750 million edge AI chips--chips or parts of chips that perform or accelerate machine learning tasks on-device, rather than in a remote data center--will be sold. This number, representing a cool US$2.6 billion in revenue, is more than twice the 300 million edge AI chips Deloitte predicted would sell in 20172--a three-year compound annual growth rate (CAGR) of 36 percent. Further, we predict that the edge AI chip market will continue to grow much more quickly than the overall chip market. By 2024, we expect sales of edge AI chips to exceed 1.5 billion, possibly by a great deal.3 This represents annual unit sales growth of at least 20 percent, more than double the longer-term forecast of 9 percent CAGR for the overall semiconductor industry.4 These edge AI chips will likely find their way into an increasing number of consumer devices, such as high-end smartphones, tablets, smart speakers, and wearables.

WIRE)--Cambridge Mobile Telematics (CMT), the world's leading mobile telematics and analytics provider, has launched its latest product line, Claims Studio. Through a lightweight smartphone solution, Claims Studio gives claims adjusters access to robust, unbiased telematics and contextual crash data after an impact occurs. CMT's ability to detect crashes has been in the market since 2015, but now has expanded to support the end-to-end claims process. Claims Studio uses telematics and artificial intelligence to reproduce the true story of a crash, creating a data-driven narrative to accelerate the claims process. By accessing key details like speed, severity, and vehicle impact location early in the process, insurers can spend less time collecting information from drivers and third parties, and more time confirming facts and accurately assessing loss.

Do you remember what Steve Jobs said about'making a dent in the universe?' Well, the way Artificial Intelligence and Big Data are improving lives it seems it would be much easier to do so with these technologies. Be it fraud prevention, automation, security, banking, and now forecasting climate change, AI and data-driven technologies are making rapid progress. Take the finance sector, for instance, AI has been serving it for years by automating and streamlining the customer experience. Additionally, AI-driven identity verification systems are detecting fraud, eliminating fraudsters, and helping banks through automation.