Multimodal classification methods using different modalities of imaging and non-imaging data have great advantages over traditional single-modality-based ones for the diagnosis and prognosis of Alzheimer's disease (AD), as well as mild cognitive impairment (MCI) which is the prodromal stage of AD. With the increasing amount of high-dimensional heterogeneous data to be processed, multi-modality feature selection has become a crucial research direction in medical image analysis. However, traditional methods usually depict the data structure using fixed and predefined similarity matrix as a priori, which is difficult to precisely measure the intrinsic relationship structure across different modalities in highdimensional spaces. In addition, based on the predefined similarity matrix, the chosen neighbors are suboptimal thus limiting the performance of the subsequent classification task. To overcome these drawbacks, in this paper, we propose a novel multi-modal feature selection method called Adaptive-Similarity-based Multi-modality Feature Selection (ASMFS) which performs adaptive similarity learning and feature selection simultaneously.

Transfer learning is an effective technique to improve a target recommender system with the knowledge from a source domain. Existing research focuses on the recommendation performance of the target domain while ignores the privacy leakage of the source domain. The transferred knowledge, however, may unintendedly leak private information of the source domain. For example, an attacker can accurately infer user demographics from their historical purchase provided by a source domain data owner. This paper addresses the above privacy-preserving issue by learning a privacy-aware neural representation by improving target performance while protecting source privacy. The key idea is to simulate the attacks during the training for protecting unseen users' privacy in the future, modeled by an adversarial game, so that the transfer learning model becomes robust to attacks. Experiments show that the proposed PrivNet model can successfully disentangle the knowledge benefitting the transfer from leaking the privacy.

Many businesses and industries require accurate forecasts for weekly time series nowadays. The forecasting literature however does not currently provide easy-to-use, automatic, reproducible and accurate approaches dedicated to this task. We propose a forecasting method that can be used as a strong baseline in this domain, leveraging state-of-the-art forecasting techniques, forecast combination, and global modelling. Our approach uses four base forecasting models specifically suitable for forecasting weekly data: a global Recurrent Neural Network model, Theta, Trigonometric Box-Cox ARMA Trend Seasonal (TBATS), and Dynamic Harmonic Regression ARIMA (DHR-ARIMA). Those are then optimally combined using a lasso regression stacking approach. We evaluate the performance of our method against a set of state-of-the-art weekly forecasting models on six datasets. Across four evaluation metrics, we show that our method consistently outperforms the benchmark methods by a considerable margin with statistical significance. In particular, our model can produce the most accurate forecasts, in terms of mean sMAPE, for the M4 weekly dataset.

Bayesian Optimisation (BO) is a popular surrogate model-based approach for optimising expensive black-box functions. In order to reduce optimisation wallclock time, parallel evaluation of the black-box function has been proposed. Asynchronous BO allows for a new evaluation to be started as soon as another finishes, thus maximising utilisation of evaluation workers. We present AEGiS (Asynchronous $\epsilon$-Greedy Global Search), an asynchronous BO method that, with probability $2\epsilon$, performs either Thompson sampling or random selection from the approximate Pareto set trading-off between exploitation (surrogate mean prediction) and exploration (surrogate posterior variance). The remaining $1-2\epsilon$ of moves exploit the surrogate's mean prediction. Results on fifteen synthetic benchmark problems, three meta-surrogate hyperparameter tuning problems and two robot pushing problems show that AEGiS generally outperforms existing methods for asynchronous BO. When a single worker is available performance is no worse than BO using expected improvement. We also verify the importance of each of the three components in an ablation study, as well as comparing Pareto set selection to selection from the entire feasible problem domain, finding that the former is vastly superior.

The interactions among the constituent members of a microbial community play a major role in determining the overall behavior of the community and the abundance levels of its members. These interactions can be modeled using a network whose nodes represent microbial taxa and edges represent pairwise interactions. A microbial network is a weighted graph that is constructed from a sample-taxa count matrix, and can be used to model co-occurrences and/or interactions of the constituent members of a microbial community. The nodes in this graph represent microbial taxa and the edges represent pairwise associations amongst these taxa. A microbial network is typically constructed from a sample-taxa count matrix that is obtained by sequencing multiple biological samples and identifying taxa counts. From large-scale microbiome studies, it is evident that microbial community compositions and interactions are impacted by environmental and/or host factors. Thus, it is not unreasonable to expect that a sample-taxa matrix generated as part of a large study involving multiple environmental or clinical parameters can be associated with more than one microbial network. However, to our knowledge, microbial network inference methods proposed thus far assume that the sample-taxa matrix is associated with a single network.

Both articles in this post came out of the George Church's lab at Harvard University. The first of them is Unified rational protein engineering with sequence-based deep representation learning. Here, the authors present a recurrent neural network (specifically, a type of mLSTM) which was trained on 24 million UniRef50 protein sequences with the objective of transforming each sequence into a numerical vector of fixed-length (that is, a deep representation). What these vectors or deep representations enable is the ability to analyze and compare protein sequences with techniques borrowed from linear algebra, as opposed to using traditional bioinformatics algorithms like sequence alignment. Next, the authors show that UniRep vectors can be used as input to train a simpler or "top" model (e.g. a linear regression) to predict the effect of single mutations.

Offered by IBM. Machine Learning is one of the most in-demand skills for jobs related to modern AI applications, a field in which hiring has grown 74% annually for the last four years (LinkedIn). This Professional Certificate from IBM is intended for anyone interested in developing skills and experience to pursue a career in Machine Learning and leverage the main types of Machine Learning: Unsupervised Learning, Supervised Learning, Deep Learning, and Reinforcement Learning. It also complements your learning with special topics, including Time Series Analysis and Survival Analysis. This program consists of 6 courses providing you with solid theoretical understanding and considerable practice of the main algorithms, uses, and best practices related to Machine Learning . You will follow along and code your own projects using some of the most relevant open source frameworks and libraries. Although it is recommended that you have some background in Python programming, statistics, and linear algebra, this intermediate series is suitable for anyone who has some computer skills, interest in leveraging data, and a passion for self-learning. We start small, provide a solid theoretical background and code-along labs and demos, and build up to more complex topics. In addition to earning a Professional Certificate from Coursera, you will also receive a digital Badge from IBM recognizing your proficiency in Machine Learning.

This article is part of "AI education", a series of posts that review and explore educational content on data science and machine learning. Teaching yourself Python machine learning can be a daunting task if you don't know where to start. Fortunately, there are plenty of good introductory books and online courses that teach you the basics. It is the advanced books, however, that teach you the skills you need to decide which algorithm better solves a problem and which direction to take when tuning hyperparameters. A while ago, I was introduced to Machine Learning Algorithms, Second Edition by Giuseppe Bonaccorso, a book that almost falls into the latter category. While the title sounds like another introductory book on machine learning algorithms, the content is anything but.

Mathematical modeling and machine learning can often feel like difficult topics to explore and learn, especially to those unfamiliar with the fields of computer science and mathematics. It surprises…

Self-training algorithms, which train a model to fit pseudolabels predicted by another previously-learned model, have been very successful for learning with unlabeled data using neural networks. However, the current theoretical understanding of self-training only applies to linear models. This work provides a unified theoretical analysis of self-training with deep networks for semi-supervised learning, unsupervised domain adaptation, and unsupervised learning. At the core of our analysis is a simple but realistic "expansion" assumption, which states that a low-probability subset of the data must expand to a neighborhood with large probability relative to the subset. We also assume that neighborhoods of examples in different classes have minimal overlap. We prove that under these assumptions, the minimizers of population objectives based on self-training and input-consistency regularization will achieve high accuracy with respect to ground-truth labels. By using off-the-shelf generalization bounds, we immediately convert this result to sample complexity guarantees for neural nets that are polynomial in the margin and Lipschitzness. Our results help explain the empirical successes of recently proposed self-training algorithms which use input consistency regularization.