We propose Deep Feature Interpolation (DFI), a new datadriven baseline for automatic high-resolution image transformation. As the name suggests, DFI relies only on simple linear interpolation of deep convolutional features from pre-trained convnets. We show that despite its simplicity, DFI can perform high-level semantic transformations like "make older/younger", "make bespectacled", "add smile", among others, surprisingly well-sometimes even matching or outperforming the state-of-the-art. This is particularly unexpected as DFI requires no specialized network architecture or even any deep network to be trained for these tasks. DFI therefore can be used as a new baseline to evaluate more complex algorithms and provides a practical answer to the question of which image transformation tasks are still challenging after the advent of deep learning.

Objectives Pure-tone audiometry has been a staple of hearing assessments for decades. Many different procedures have been proposed for measuring thresholds with pure tones by systematically manipulating intensity one frequency at a time until a discrete threshold function is determined. The authors have developed a novel nonparametric approach for estimating a continuous threshold audiogram using Bayesian estimation and machine learning classification. The objective of this study is to assess the accuracy and reliability of this new method relative to a commonly used threshold measurement technique. Design The authors performed air conduction pure-tone audiometry on 21 participants between the ages of 18 and 90 years with varying degrees of hearing ability. Two repetitions of automated machine learning audiogram estimation and 1 repetition of conventional modified Hughson-Westlake ascending-descending audiogram estimation were acquired by an audiologist. The estimated hearing thresholds of these two techniques were compared at standard audiogram frequencies (i.e., 0.25, 0.5, 1, 2, 4, 8 kHz). Results The two threshold estimate methods delivered very similar estimates at standard audiogram frequencies. Specifically, the mean absolute difference between estimates was 4.16 ± 3.76 dB HL. The mean absolute difference between repeated measurements of the new machine learning procedure was 4.51 ± 4.45 dB HL. These values compare favorably to those of other threshold audiogram estimation procedures. Furthermore, the machine learning method generated threshold estimates from significantly fewer samples than the modified Hughson-Westlake procedure while returning a continuous threshold estimate as a function of frequency. Conclusions The new machine learning audiogram estimation technique produces continuous threshold audiogram estimates accurately, reliably, and efficiently, making it a strong candidate for widespread application in clinical and research audiometry.

No abstract

No abstract

Many tasks in computer vision can be cast as a "label changing" problem, where the goal is to make a semantic change to the appearance of an image or some subject in an image in order to alter the class membership. Although successful task-specific methods have been developed for some label changing applications, to date no general purpose method exists. Motivated by this we propose deep manifold traversal, a method that addresses the problem in its most general form: it first approximates the manifold of natural images then morphs a test image along a traversal path away from a source class and towards a target class while staying near the manifold throughout. The resulting algorithm is surprisingly effective and versatile. It is completely data driven, requiring only an example set of images from the desired source and target domains. We demonstrate deep manifold traversal on highly diverse label changing tasks: changing an individual's appearance (age and hair color), changing the season of an outdoor image, and transforming a city skyline towards nighttime.

Algorithmic reductions are one of the corner stones of theoretical computer science. Surprisingly, to-date, they have only played a limited role in machine learning. In this paper we introduce a formal and practical reduction between two of the most widely used machine learning algorithms: from the Elastic Net (and the Lasso as a special case) to the Support Vector Machine. First, we derive the reduction and summarize it in only 11 lines of MATLAB. Then, we demonstrate its high impact potential by translating recent advances in parallelizing SVM solvers directly to the Elastic Net. The resulting algorithm is a parallel solver for the Elastic Net (and Lasso) that naturally utilizes GPU and multi-core CPUs. We evaluate it on twelve real world data sets, and show that it yields identical results as the popular (and highly optimized) glmnet implementation but is up-to two orders of magnitude faster.

Epigenetic changes, such as aberrant DNA methylation, contribute to cancer clonal expansion and disease progression. However, identifying subpopulation-level changes in a heterogeneous sample remains challenging. Thus, we have developed a computational approach, DXM, to deconvolve the methylation profiles of major allelic subpopulations from the bisulfite sequencing data of a heterogeneous sample. DXM does not require prior knowledge of the number of subpopulations or types of cells to expect. We benchmark DXM’s performance and demonstrate improvement over existing methods. We further experimentally validate DXM predicted allelic subpopulation-methylation profiles in four Diffuse Large B-Cell Lymphomas (DLBCLs). Lastly, as proof-of-concept, we apply DXM to a cohort of 31 DLBCLs and relate allelic subpopulation methylation profiles to relapse. We thus demonstrate that DXM can robustly find allelic subpopulation methylation profiles that may contribute to disease progression using bisulfite sequencing data of any heterogeneous sample.

Gaussian processes (GPs) are flexible non-parametric models, with a capacity that grows with the available data. However, computational constraints with standard inference procedures have limited exact GPs to problems with fewer than about ten thousand training points, necessitating approximations for larger datasets. In this paper, we develop a scalable approach for exact GPs that leverages multi-GPU parallelization and methods like linear conjugate gradients, accessing the kernel matrix only through matrix multiplication. By partitioning and distributing kernel matrix multiplies, we demonstrate that an exact GP can be trained on over a million points, a task previously thought to be impossible with current computing hardware, in less than 2 hours. Moreover, our approach is generally applicable, without constraints to grid data or specific kernel classes. Enabled by this scalability, we perform the first-ever comparison of exact GPs against scalable GP approximations on datasets with 10 4 − 10 6 data points, showing dramatic performance improvements.