Electronic health records (EHR) are increasingly being used for constructing disease risk prediction models. Feature engineering in EHR data however is challenging due to their highly dimensional and heterogeneous nature. Low-dimensional representations of EHR data can potentially mitigate these challenges. In this paper, we use global vectors (GloVe) to learn word embeddings for diagnoses and procedures recorded using 13 million ontology terms across 2.7 million hospitalisations in national UK EHR. We demonstrate the utility of these embeddings by evaluating their performance in identifying patients which are at higher risk of being hospitalised for congestive heart failure. Our findings indicate that embeddings can enable the creation of robust EHR-derived disease risk prediction models and address some the limitations associated with manual clinical feature engineering.

Class-imbalance refers to classification problems in which many more instances are available for certain classes than for others. Such imbalanced datasets require special attention because traditional classifiers generally favor the majority class which has a large number of instances. Ensemble of classifiers have been reported to yield promising results. However, the majority of ensemble methods applied to imbalanced learning are static ones. Moreover, they only deal with binary imbalanced problems. Hence, this paper presents an empirical analysis of dynamic selection techniques and data preprocessing methods for dealing with multi-class imbalanced problems. We considered five variations of preprocessing methods and fourteen dynamic selection schemes. Our experiments conducted on 26 multi-class imbalanced problems show that the dynamic ensemble improves the AUC and the G-mean as compared to the static ensemble. Moreover, data preprocessing plays an important role in such cases.

Stochastic gradient descent updates parameters with summation gradient computed from a random data batch. This summation will lead to unbalanced training process if the data we obtained is unbalanced. To address this issue, this paper takes the error variance and error mean both into consideration. The adaptively adjusting approach of two terms trading off is also given in our algorithm. Due to this algorithm can suppress error variance, we named it Variance Suppression Gradient Descent (VSSGD). Experimental results have demonstrated that VSSGD can accelerate the training process, effectively prevent overfitting, improve the networks learning capacity from small samples.

Few-shot or one-shot learning of classifiers for images or videos is an important next frontier in computer vision. The extreme paucity of training data means that the learning must start with a significant inductive bias towards the type of task to be learned. One way to acquire this is by meta-learning on tasks similar to the target task. However, if the meta-learning phase requires labeled data for a large number of tasks closely related to the target task, it not only increases the difficulty and cost, but also conceptually limits the approach to variations of well-understood domains. In this paper, we propose UMTRA, an algorithm that performs meta-learning on an unlabeled dataset in an unsupervised fashion, without putting any constraint on the classifier network architecture. The only requirements towards the dataset are: sufficient size, diversity and number of classes, and relevance of the domain to the one in the target task. Exploiting this information, UMTRA generates synthetic training tasks for the meta-learning phase. We evaluate UMTRA on few-shot and one-shot learning on both image and video domains. To the best of our knowledge, we are the first to evaluate meta-learning approaches on UCF-101. On the Omniglot and Mini-Imagenet few-shot learning benchmarks, UMTRA outperforms every tested approach based on unsupervised learning of representations, while alternating for the best performance with the recent CACTUs algorithm. Compared to supervised model-agnostic meta-learning approaches, UMTRA trades off some classification accuracy for a vast decrease in the number of labeled data needed. For instance, on the five-way one-shot classification on the Omniglot, we retain 85% of the accuracy of MAML, a recently proposed supervised meta-learning algorithm, while reducing the number of required labels from 24005 to 5.

Continual learning is the problem of learning new tasks or knowledge while protecting old knowledge and ideally generalizing from old experience to learn new tasks faster. Neural networks trained by stochastic gradient descent often degrade on old tasks when trained successively on new tasks with different data distributions. This phenomenon, referred to as catastrophic forgetting, is considered a major hurdle to learning with non-stationary data or sequences of new tasks, and prevents networks from continually accumulating knowledge and skills. We examine this issue in the context of reinforcement learning, in a setting where an agent is exposed to tasks in a sequence. Unlike most other work, we do not provide an explicit indication to the model of task boundaries, which is the most general circumstance for a learning agent exposed to continuous experience. While various methods to counteract catastrophic forgetting have recently been proposed, we explore a straightforward, general, and seemingly overlooked solution - that of using experience replay buffers for all past events - with a mixture of on- and off-policy learning, leveraging behavioral cloning. We show that this strategy can still learn new tasks quickly yet can substantially reduce catastrophic forgetting in both Atari and DMLab domains, even matching the performance of methods that require task identities. When buffer storage is constrained, we confirm that a simple mechanism for randomly discarding data allows a limited size buffer to perform almost as well as an unbounded one.

It has long been observed that for practically any computational problem that has been intensely studied, different instances are best solved using different algorithms. This is particularly pronounced for computationally hard problems, where in most cases, no single algorithm defines the state of the art; instead, there is a set of algorithms with complementary strengths. This performance complementarity can be exploited in various ways, one of which is based on the idea of selecting, from a set of given algorithms, for each problem instance to be solved the one expected to perform best. The task of automatically selecting an algorithm from a given set is known as the per-instance algorithm selection problem and has been intensely studied over the past 15 years, leading to major improvements in the state of the art in solving a growing number of discrete combinatorial problems, including propositional satisfiability and AI planning. Per-instance algorithm selection also shows much promise for boosting performance in solving continuous and mixed discrete/continuous optimisation problems. This survey provides an overview of research in automated algorithm selection, ranging from early and seminal works to recent and promising application areas. Different from earlier work, it covers applications to discrete and continuous problems, and discusses algorithm selection in context with conceptually related approaches, such as algorithm configuration, scheduling or portfolio selection. Since informative and cheaply computable problem instance features provide the basis for effective per-instance algorithm selection systems, we also provide an overview of such features for discrete and continuous problems. Finally, we provide perspectives on future work in the area and discuss a number of open research challenges.

The project is about predicting coronary heart disease by using three different ML algorithms. And to know which is the best approach. There are roughly two controls per case of CHD. Many of the CHD positive men have undergone blood pressure reduction treatment and other programs to reduce their risk factors after their occurrence of CHD. In some cases the measurements were made after these treatments.

Distributed learning systems have enabled training large-scale models over large amount of data in significantly shorter time. In this paper, we focus on decentralized distributed deep learning systems and aim to achieve differential privacy with good convergence rate and low communication cost. To achieve this goal, we propose a new learning algorithm LEASGD (Leader-Follower Elastic Averaging Stochastic Gradient Descent), which is driven by a novel Leader-Follower topology and a differential privacy model. We provide a theoretical analysis of the convergence rate and the tradeoff between the performance and privacy in the private setting. The experimental results show that LEASGD outperforms state-of-the-art decentralized learning algorithm DPSGD by achieving steadily lower loss within the same iterations and by reducing the communication cost by 30%. In addition, LEASGD spends less differential privacy budget and has higher final accuracy result than DPSGD under private setting.

We introduce the Metropolis-Hastings generative adversarial network (MH-GAN), which combines aspects of Markov chain Monte Carlo and GANs. The MH-GAN draws samples from the distribution implicitly defined by a GAN's discriminator-generator pair, as opposed to sampling in a standard GAN which draws samples from the distribution defined by the generator. It uses the discriminator from GAN training to build a wrapper around the generator for improved sampling. With a perfect discriminator, this wrapped generator samples from the true distribution on the data exactly even when the generator is imperfect. We demonstrate the benefits of the improved generator on multiple benchmark datasets, including CIFAR-10 and CelebA, using DCGAN and WGAN.

Spectral mixture kernels have been proposed as general-purpose, flexible kernels for learning and discovering more complicated patterns in the data. Spectral mixture kernels have recently been generalized into non-stationary kernels by replacing the mixture weights, frequency means and variances by input-dependent functions. These functions have also been modelled as Gaussian processes on their own. In this paper we propose modelling the hyperparameter functions with neural networks, and provide an experimental comparison between the stationary spectral mixture and the two non-stationary spectral mixtures. Scalable Gaussian process inference is implemented within the sparse variational framework for all the kernels considered. We show that the neural variant of the kernel is able to achieve the best performance, among alternatives, on several benchmark datasets.