Computational single-cell RNA-seq (scRNA-seq) methods have been successfully applied to experiments representing a single condition, technology, or species to discover and define cellular phenotypes. However, identifying subpopulations of cells that are present across multiple data sets remains challenging. Here, we introduce an analytical strategy for integrating scRNA-seq data sets based on common sources of variation, enabling the identification of shared populations across data sets and downstream comparative analysis. We apply this approach, implemented in our R toolkit Seurat (http://satijalab.org/seurat/), to align scRNA-seq data sets of peripheral blood mononuclear cells under resting and stimulated conditions, hematopoietic progenitors sequenced using two profiling technologies, and pancreatic cell 'atlases' generated from human and mouse islets. In each case, we learn distinct or transitional cell states jointly across data sets, while boosting statistical power through integrated analysis. Our approach facilitates general comparisons of scRNA-seq data sets, potentially deepening our understanding of how distinct cell states respond to perturbation, disease, and evolution.

/pdf/integrating-single-cell-transcriptomic-data-across-different-3dtsi5w7ob.pdf

Integrating single-cell transcriptomic data across different conditions, technologies, and species.

Kernel methods provide a powerful and unified framework for pattern discovery, motivating algorithms that can act on general types of data (e.g. strings, vectors or text) and look for general types of relations (e.g. rankings, classifications, regressions, clusters). The application areas range from neural networks and pattern recognition to machine learning and data mining. This book, developed from lectures and tutorials, fulfils two major roles: firstly it provides practitioners with a large toolkit of algorithms, kernels and solutions ready to use for standard pattern discovery problems in fields such as bioinformatics, text analysis, image analysis. Secondly it provides an easy introduction for students and researchers to the growing field of kernel-based pattern analysis, demonstrating with examples how to handcraft an algorithm or a kernel for a new specific application, and covering all the necessary conceptual and mathematical tools to do so.

/pdf/kernel-methods-for-pattern-analysis-3ta60xrj0i.pdf

Kernel Methods for Pattern Analysis

The Fisher kernel (FK) is a generic framework which combines the benefits of generative and discriminative approaches. In the context of image classification the FK was shown to extend the popular bag-of-visual-words (BOV) by going beyond count statistics. However, in practice, this enriched representation has not yet shown its superiority over the BOV. In the first part we show that with several well-motivated modifications over the original framework we can boost the accuracy of the FK. On PASCAL VOC 2007 we increase the Average Precision (AP) from 47.9% to 58.3%. Similarly, we demonstrate state-of-the-art accuracy on CalTech 256. A major advantage is that these results are obtained using only SIFT descriptors and costless linear classifiers. Equipped with this representation, we can now explore image classification on a larger scale. In the second part, as an application, we compare two abundant resources of labeled images to learn classifiers: ImageNet and Flickr groups. In an evaluation involving hundreds of thousands of training images we show that classifiers learned on Flickr groups perform surprisingly well (although they were not intended for this purpose) and that they can complement classifiers learned on more carefully annotated datasets.

/pdf/improving-the-fisher-kernel-for-large-scale-image-20pl2r6uxa.pdf

Improving the fisher kernel for large-scale image classification

Deep networks have been successfully applied to unsupervised feature learning for single modalities (e.g., text, images or audio). In this work, we propose a novel application of deep networks to learn features over multiple modalities. We present a series of tasks for multimodal learning and show how to train deep networks that learn features to address these tasks. In particular, we demonstrate cross modality feature learning, where better features for one modality (e.g., video) can be learned if multiple modalities (e.g., audio and video) are present at feature learning time. Furthermore, we show how to learn a shared representation between modalities and evaluate it on a unique task, where the classifier is trained with audio-only data but tested with video-only data and vice-versa. Our models are validated on the CUAVE and AVLetters datasets on audio-visual speech classification, demonstrating best published visual speech classification on AVLetters and effective shared representation learning.

/pdf/multimodal-deep-learning-2qi0e2kef0.pdf

Multimodal Deep Learning

Our experience of the world is multimodal - we see objects, hear sounds, feel texture, smell odors, and taste flavors Modality refers to the way in which something happens or is experienced and a research problem is characterized as multimodal when it includes multiple such modalities In order for Artificial Intelligence to make progress in understanding the world around us, it needs to be able to interpret such multimodal signals together Multimodal machine learning aims to build models that can process and relate information from multiple modalities It is a vibrant multi-disciplinary field of increasing importance and with extraordinary potential Instead of focusing on specific multimodal applications, this paper surveys the recent advances in multimodal machine learning itself and presents them in a common taxonomy We go beyond the typical early and late fusion categorization and identify broader challenges that are faced by multimodal machine learning, namely: representation, translation, alignment, fusion, and co-learning This new taxonomy will enable researchers to better understand the state of the field and identify directions for future research

Multimodal Machine Learning: A Survey and Taxonomy

We present a general method using kernel canonical correlation analysis to learn a semantic representation to web images and their associated text. The semantic space provides a common representation and enables a comparison between the text and images. In the experiments, we look at two approaches of retrieving images based on only their content from a text query. We compare orthogonalization approaches against a standard cross-representation retrieval technique known as the generalized vector space model.

/pdf/canonical-correlation-analysis-an-overview-with-application-2zvylpnrdn.pdf

Canonical Correlation Analysis: An Overview with Application to Learning Methods

In this paper we propose two distinct enhancements to the basic “bag-of-keypoints” image categorisation scheme proposed in [4] In this approach images are represented as a variable sized set of local image features (keypoints) Thus, we require machine learning tools which can operate on sets of vectors In [4] this is achieved by representing the set as a histogram over bins found by k-means We show how this approach can be improved and generalised using Gaussian Mixture Models (GMMs) Alternatively, the set of keypoints can be represented directly as a probability density function, over which a kernel can be defined This approach is shown to give state of the art categorisation performance

/pdf/improving-bag-of-keypoints-image-categorisation-generative-46yu02mi8q.pdf

Improving "bag-of-keypoints" image categorisation: Generative Models and PDF-Kernels

Multiclass classification by L1 norm Support Vector Machine

We present a general and e!cien t optimization methodology for max-margin structured classification tasks The e!ciency of the method relies on the interplay of several techniques: formulation of the structured support vector machine or maxmargin Markov problem as an optimization problem; marginalization of the dual of the optimization; partial decomposition via a gradient formulation; and finally tight coupling of a maximum likelihood inference algorithm into the optimization algorithm, as opposed to using inference as a working set maintenance mechanism only The tight coupling also allows fast approximate inference to be used e"ectiv ely in the learning The generality of the method follows from the fact that changing the output structure in essence only changes the inference algorithm, that is, the method can to a large extent be used in a ‘plug and play’ fashion

John Shawe-Taylor

Papers

Canonical Correlation Analysis: An Overview with Application to Learning Methods

Improving "bag-of-keypoints" image categorisation: Generative Models and PDF-Kernels

Multiclass classification by L1 norm Support Vector Machine

Efficient Algorithms for Max-Margin Structured Classification

Multiplicative Updatings for Support Vector Machines