America's agricultural sector faces an unprecedented crisis. Native honeybees, one of the most prolific pollinators in the animal kingdom, are dying off at an unprecedented rate from Colony Collapse Disorder (CCD), threatening an ecosystem service worth about $15 billion. Supported by the National Science Foundation (NSF), the "RoboBees" project looks to minimize the loss of this critical resource with remarkable microbots that can mimic the pollinating role of a honeybee. But the project has a number of challenges to overcome before these robots can take to the skies. The RoboBee is a microrobot inspired by the biology of a honey bee.

Dr Stephen Weng, from the university's NIHR School for Primary Care Research, said: "Cardiovascular disease is the leading cause of illness and death worldwide. Our study shows that artificial intelligence could significantly help in the fight against it by improving the number of patients accurately identified as being at high risk and allowing for early intervention by doctors to prevent serious events like cardiac arrest and stroke. "Current standard prediction models like the ACC are based on eight risk factors including age, cholesterol level and blood pressure but are too simplistic to account for other factors like medications, multiple disease conditions, and other non-traditional biomarkers. These AI algorithms have the potential to help save more lives". Professor Jon Garibaldi and Dr Jenna Reps, of the Advanced Data Analysis Centre in the School of Computer Science, said: "We were curious to find out how four modern machine learning algorithms would perform given the large data set of 378,256 patients from nearly 700 UK GP practices.

Learn key AI concepts and intuition training to get you quickly up to speed with all things AI. Every tutorial starts with a blank page and we write up the code from scratch. This way you can follow along and understand exactly how the code comes together and what each line means. This makes building truly unique AI as simple as changing a few lines of code. If you unleash your imagination, the potential is unlimited.

Reinforcement learning studies how to balance exploration and exploitation in real-world systems, optimizing interactions with the world while simultaneously learning how the world works. One general class of algorithms for such learning is the multi-armed bandit setting (in which sequential interactions are independent and identically distributed) and the related contextual bandit case, in which the distribution depends on different information or 'context' presented with each interaction. Thompson sampling, though introduced in the 1930s, has recently been shown to perform well and to enjoy provable optimality properties, while at the same time permitting generative, interpretable modeling. In a Bayesian setting, prior knowledge is incorporated and the computed posteriors naturally capture the full state of knowledge. In several application domains, for example in health and medicine, each interaction with the world can be expensive and invasive, whereas drawing samples from the model is relatively inexpensive. Exploiting this viewpoint, we develop a double-sampling technique driven by the uncertainty in the learning process. The proposed algorithm does not make any distributional assumption and it is applicable to complex reward distributions, as long as Bayesian posterior updates are computable. We empirically show that it out-performs (in the sense of regret) Thompson sampling in two classical illustrative cases, i.e., the multi-armed bandit problem with and without context.

In many biomedical, science, and engineering problems, one must sequentially decide which action to take next so as to maximize rewards. Reinforcement learning is an area of machine learning that studies how this maximization balances exploration and exploitation, optimizing interactions with the world while simultaneously learning how the world operates. One general class of algorithms for this type of learning is the multi-armed bandit setting and, in particular, the contextual bandit case, in which observed rewards are dependent on each action as well as on given information or 'context' available at each interaction with the world. The Thompson sampling algorithm has recently been shown to perform well in real-world settings and to enjoy provable optimality properties for this set of problems. It facilitates generative and interpretable modeling of the problem at hand, though complexity of the model limits its application, since one must both sample from the distributions modeled and calculate their expected rewards. We here show how these limitations can be overcome using variational approximations, applying to the reinforcement learning case advances developed for the inference case in the machine learning community over the past two decades. We consider bandit applications where the true reward distribution is unknown and approximate it with a mixture model, whose parameters are inferred via variational inference.

Semi-supervised active clustering (SSAC) utilizes the knowledge of a domain expert to cluster data points by interactively making pairwise "same-cluster" queries. However, it is impractical to ask human oracles to answer every pairwise query. In this paper, we study the influence of allowing "not-sure" answers from a weak oracle and propose algorithms to efficiently handle uncertainties. Different types of model assumptions are analyzed to cover realistic scenarios of oracle abstraction. In the first model, random-weak oracle, an oracle randomly abstains with a certain probability. We also proposed two distance-weak oracle models which simulate the case of getting confused based on the distance between two points in a pairwise query. For each weak oracle model, we show that a small query complexity is adequate for the effective $k$ means clustering with high probability. Sufficient conditions for the guarantee include a $\gamma$-margin property of the data, and an existence of a point close to each cluster center. Furthermore, we provide a sample complexity with a reduced effect of the cluster's margin and only a logarithmic dependency on the data dimension. Our results allow significantly less number of same-cluster queries if the margin of the clusters is tight, i.e. $\gamma \approx 1$. Experimental results on synthetic data show the effective performance of our approach in overcoming uncertainties.

This paper studies the problem of estimating the grahpon model - the underlying generating mechanism of a network. Graphon estimation arises in many applications such as predicting missing links in networks and learning user preferences in recommender systems. The graphon model deals with a random graph of $n$ vertices such that each pair of two vertices $i$ and $j$ are connected independently with probability $\rho \times f(x_i,x_j)$, where $x_i$ is the unknown $d$-dimensional label of vertex $i$, $f$ is an unknown symmetric function, and $\rho$ is a scaling parameter characterizing the graph sparsity. Recent studies have identified the minimax error rate of estimating the graphon from a single realization of the random graph. However, there exists a wide gap between the known error rates of computationally efficient estimation procedures and the minimax optimal error rate. Here we analyze a spectral method, namely universal singular value thresholding (USVT) algorithm, in the relatively sparse regime with the average vertex degree $n\rho=\Omega(\log n)$. When $f$ belongs to H\"{o}lder or Sobolev space with smoothness index $\alpha$, we show the error rate of USVT is at most $(n\rho)^{ -2 \alpha / (2\alpha+d)}$, approaching the minimax optimal error rate $\log (n\rho)/(n\rho)$ for $d=1$ as $\alpha$ increases. Furthermore, when $f$ is analytic, we show the error rate of USVT is at most $\log^d (n\rho)/(n\rho)$. In the special case of stochastic block model with $k$ blocks, the error rate of USVT is at most $k/(n\rho)$, which is larger than the minimax optimal error rate by at most a multiplicative factor $k/\log k$. This coincides with the computational gap observed for community detection. A key step of our analysis is to derive the eigenvalue decaying rate of the edge probability matrix using piecewise polynomial approximations of the graphon function $f$.

Multivariate time-series modeling and forecasting is an important problem with numerous applications. Traditional approaches such as VAR (vector auto-regressive) models and more recent approaches such as RNNs (recurrent neural networks) are indispensable tools in modeling time-series data. In many multivariate time series modeling problems, there is usually a significant linear dependency component, for which VARs are suitable, and a nonlinear component, for which RNNs are suitable. Modeling such times series with only VAR or only RNNs can lead to poor predictive performance or complex models with large training times. In this work, we propose a hybrid model called R2N2 (Residual RNN), which first models the time series with a simple linear model (like VAR) and then models its residual errors using RNNs. R2N2s can be trained using existing algorithms for VARs and RNNs. Through an extensive empirical evaluation on two real world datasets (aviation and climate domains), we show that R2N2 is competitive, usually better than VAR or RNN, used alone. We also show that R2N2 is faster to train as compared to an RNN, while requiring less number of hidden units.

This paper presents a deep learning method for faster magnetic resonance imaging (MRI) by reducing k-space data with sub-Nyquist sampling strategies and provides a rationale for why the proposed approach works well. Uniform subsampling is used in the time-consuming phase-encoding direction to capture high-resolution image information, while permitting the image-folding problem dictated by the Poisson summation formula. To deal with the localization uncertainty due to image folding, very few low-frequency k-space data are added. Training the deep learning net involves input and output images that are pairs of Fourier transforms of the subsampled and fully sampled k-space data. Numerous experiments show the remarkable performance of the proposed method; only 29% of k-space data can generate images of high quality as effectively as standard MRI reconstruction with fully sampled data.

We propose a new algorithm called Parle for parallel training of deep networks that converges 2-4x faster than a data-parallel implementation of SGD, while achieving significantly improved error rates that are nearly state-of-the-art on several benchmarks including CIFAR-10 and CIFAR-100, without introducing any additional hyper-parameters. We exploit the phenomenon of flat minima that has been shown to lead to improved generalization error for deep networks. Parle requires very infrequent communication with the parameter server and instead performs more computation on each client, which makes it well-suited to both single-machine, multi-GPU settings and distributed implementations.