Abstract--Multi-view learning improves the learning performance by utilizing multi-view data: data collected from mul tiple sources, or feature sets extracted from the same data source . This approach is suitable for primate brain state decoding using cortical neural signals. This is because the compleme ntary components of simultaneously recorded neural signals, loc al field potentials (LFPs) and action potentials (spikes), can be tr eated as two views. In this paper, we extended broad learning syste m (BLS), a recently proposed wide neural network architectur e, from single-view learning to multi-view learning, and vali dated its performance in monkey oculomotor decision decoding fro m medial frontal LFPs and spikes. We demonstrated that medial frontal LFPs and spikes in nonhuman primate do contain complementary information about the oculomotor decision, and that the proposed multi-view BLS is a more effective approac h to classify the oculomotor decision, than several classica l and state-of-the-art single-view and multi-view learning app roaches. UL TIview learning attempts to improve the learning performance by utilizing multi-view data, which can be collected from multiple data sources, or different featu re sets extracted from the same data source. For example, in an invasive brain-machine interface (BMI) using electrode s [1], effective BMI cursor control can be achieved using acti on potentials (spikes), which are high-pass filtered neural si gnals, or local field potentials (LFPs), which are low-pass filtered neural signals measured from the same electrodes. The spike s and LFPs can represent two views of the same task. There have been a few studies on applying multi-view learning to human brain state decoding. Kandemir et al. [2] combined multi-task learning and multi-view learning i n decoding a user's affective state, by treating different ty pes He and D. Wu are with the Key Laboratory of Im age Processing and Intelligent Control (Huazhong University o f Science and Technology), Ministry of Education.

Object detection is a computer vision technique whose aim is to detect objects such as cars, buildings, and human beings, just to mention a few. The objects can generally be identified from either pictures or video feeds. Object detection has been applied widely in video surveillance, self-driving cars, and object/people tracking. In this piece, we'll look at the basics of object detection and review some of the most commonly-used algorithms and a few brand new approaches, as well. Object detection locates the presence of an object in an image and draws a bounding box around that object.

One aim of data mining is the identification of interesting structures in data. Basic properties of the empirical distribution, such as skewness and an eventual clipping, i.e., hard limits in value ranges, need to be assessed. Of particular interest is the question, whether the data originates from one process, or contains subsets related to different states of the data producing process. Data visualization tools should deliver a sensitive picture of the univariate probability density distribution (PDF) for each feature. Visualization tools for PDFs are typically kernel density estimates and range from the classical histogram to modern tools like bean or violin plots. Conventional methods have difficulties in visualizing the pdf in case of uniform, multimodal, skewed and clipped data if density estimation parameters remain in a default setting. As a consequence, a new visualization tool called Mirrored Density plot (MD plot) is proposed which is particularly designed to discover interesting structures in continuous features. The MD plot does not require any adjustments of parameters of density estimation which makes the usage compelling for non-experts. The visualization tools are evaluated in comparison to statistical tests for the typical challenges of explorative distribution analysis. The results are presented on bimodal Gaussian and skewed distributions as well as several features with published pdfs. In exploratory data analysis of 12 features describing the quarterly financial statements, when statistical testing becomes a demanding task, only the MD plots can identify the structure of their pdfs. Overall, the MD plot can outperform the methods mentioned above.

The main contribution of the paper is to show that Gaussian sketching of a kernel-Gram matrix $\mathbf{K}$ yields an operator whose counterpart in an RKHS $\mathcal{H}$, is a random projection operator---in the spirit of Johnson-Lindenstrauss (JL) lemma. To be precise, given a random matrix $Z$ with i.i.d. Gaussian entries, we show that a sketch $Z\mathbf{K}$ corresponds to a particular random operator in (infinite-dimensional) Hilbert space $\mathcal{H}$ that maps functions $f \in \mathcal{H}$ to a low-dimensional space $\mathbb{R}^d$, while preserving a weighted RKHS inner-product of the form $\langle f, g \rangle_{\Sigma} \doteq \langle f, \Sigma^3 g \rangle_{\mathcal{H}}$, where $\Sigma$ is the \emph{covariance} operator induced by the data distribution. In particular, under similar assumptions as in kernel PCA (KPCA), or kernel $k$-means (K-$k$-means), well-separated subsets of feature-space $\{K(\cdot, x): x \in \cal X\}$ remain well-separated after such operation, which suggests similar benefits as in KPCA and/or K-$k$-means, albeit at the much cheaper cost of a random projection. In particular, our convergence rates suggest that, given a large dataset $\{X_i\}_{i=1}^N$ of size $N$, we can build the Gram matrix $\mathbf{K}$ on a much smaller subsample of size $n\ll N$, so that the sketch $Z\mathbf{K}$ is very cheap to obtain and subsequently apply as a projection operator on the original data $\{X_i\}_{i=1}^N$. We verify these insights empirically on synthetic data, and on real-world clustering applications.

Multitask learning and transfer learning have proven to be useful in the field of machine learning when additional knowledge is available to help a prediction task. We aim at deriving methods following these paradigms for use in autotuning, where the goal is to find the optimal performance parameters of an application treated as a black-box function. We show comparative results with state-of-the-art autotuning techniques. For instance, we observe an average $1.5x$ improvement of the application runtime compared to the OpenTuner and HpBandSter autotuners. We explain how our approaches can be more suitable than some state-of-the-art autotuners for the tuning of any application in general and of expensive exascale applications in particular.

Min-max optimization has attracted much attention in the machine learning community due to the popularization of deep generative models and adversarial training. The optimization is quite different from traditional minimization analysis. For example, gradient descent does not converge in one of the simplest settings -- bilinear games. In this paper, we try to understand several gradient-based algorithms for bilinear min-max games: gradient descent, extra-gradient, optimistic gradient descent and the momentum method, for both simultaneous and alternating updates. We provide necessary and sufficient conditions for their convergence, with the Schur theorem. Furthermore, by extending these algorithms to more general parameter settings, we are able to optimize over larger parameter spaces to find the optimal convergence rates. Our results imply that alternating updates converge more easily in min-max games than simultaneous updates.

Department of Pharmaceutical Biosciences Uppsala University, Uppsala, Sweden Abstract Conformal Prediction is a framework that produces prediction intervals based on the output from a machine learning algorithm. In this paper we explore the case when training data is made up of multiple parts available in different sources that cannot be pooled. We here consider the regression case and propose a method where a conformal predictor is trained on each data source independently, and where the prediction intervals are then combined into a single interval. We call the approach Non-Disclosed Conformal Prediction (NDCP), and we evaluate it on a regression dataset from the UCI machine learning repository using support vector regression as the underlying machine learning algorithm, with varying number of data sources and sizes. The results show that the proposed method produces conservatively valid prediction intervals, and while we cannot retain the same efficiency as when all data is used, efficiency is improved through the proposed approach as compared to predicting using a single arbitrarily chosen source.

Of the 2652 articles considered, 106 met the inclusion criteria. Review of the included papers resulted in identification of 43 chronic diseases, which were then further classified into 10 disease categories using ICD-10. The majority of studies focused on diseases of the circulatory system (n=38) while endocrine and metabolic diseases were fewest (n=14). This was due to the structure of clinical records related to metabolic diseases, which typically contain much more structured data, compared with medical records for diseases of the circulatory system, which focus more on unstructured data and consequently have seen a stronger focus of NLP. The review has shown that there is a significant increase in the use of machine learning methods compared to rule-based approaches; however, deep learning methods remain emergent (n=3). Consequently, the majority of works focus on classification of disease phenotype with only a handful of papers addressing extraction of comorbidities from the free text or integration of clinical notes with structured data. There is a notable use of relatively simple methods, such as shallow classifiers (or combination with rule-based methods), due to the interpretability of predictions, which still represents a significant issue for more complex methods. Finally, scarcity of publicly available data may also have contributed to insufficient development of more advanced methods, such as extraction of word embeddings from clinical notes. Further efforts are still required to improve (1) progression of clinical NLP methods from extraction toward understanding; (2) recognition of relations among entities rather than entities in isolation; (3) temporal extraction to understand past, current, and future clinical events; (4) exploitation of alternative sources of clinical knowledge; and (5) availability of large-scale, de-identified clinical corpora.

Prior work has demonstrated that question classification (QC), recognizing the problem domain of a question, can help answer it more accurately. However, developing strong QC algorithms has been hindered by the limited size and complexity of annotated data available. To address this, we present the largest challenge dataset for QC, containing 7,787 science exam questions paired with detailed classification labels from a fine-grained hierarchical taxonomy of 406 problem domains. We then show that a BERT-based model trained on this dataset achieves a large (+0.12 MAP) gain compared with previous methods, while also achieving state-of-the-art performance on benchmark open-domain and biomedical QC datasets. Finally, we show that using this model's predictions of question topic significantly improves the accuracy of a question answering system by +1.7% P@1, with substantial future gains possible as QC performance improves.

Multimodal learning aims to discover the relationship between multiple modalities. It has become an important research topic due to extensive multimodal applications such as cross-modal retrieval. This paper attempts to address the modality heterogeneity problem based on Gaussian process latent variable models (GPLVMs) to represent multimodal data in a common space. Previous multimodal GPLVM extensions generally adopt individual learning schemes on latent representations and kernel hyperparameters, which ignore their intrinsic relationship. To exploit strong complementarity among different modalities and GPLVM components, we develop a novel learning scheme called Harmonization, where latent model parameters are jointly learned from each other. Beyond the correlation fitting or intra-modal structure preservation paradigms widely used in existing studies, the harmonization is derived in a model-driven manner to encourage the agreement between modality-specific GP kernels and the similarity of latent representations. We present a range of multimodal learning models by incorporating the harmonization mechanism into several representative GPLVM-based approaches. Experimental results on four benchmark datasets show that the proposed models outperform the strong baselines for cross-modal retrieval tasks, and that the harmonized multimodal learning method is superior in discovering semantically consistent latent representation.