Jacob R. Gardner

Deep Feature Interpolation for Image Content Changes

We propose Deep Feature Interpolation (DFI), a new data-driven 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.

Fast, Continuous Audiogram Estimation Using Machine 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 was 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 one 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 with 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.

WOODSTOCC: Extracting Latent Parallelism from a DNA Sequence Aligner on a GPU

An exponential increase in the speed of DNA sequencing over the past decade has driven demand for fast, space efficient algorithms to process the resultant data. The first step in processing is alignment of many short DNA sequences, or reads, against a large reference sequence. This work presents WOODSTOCC, an implementation of short-read alignment designed for Graphics Processing Unit (GPU) architectures. WOODSTOCC translates a novel CPU implementation of gapped short-read alignment, which has guaranteed optimal and complete results, to the GPU. Our implementation combines an irregular trie search with dynamic programming to expose regularly structured parallelism. We first describe this implementation, then discuss its port to the GPU. WOODSTOCCs GPU port exploits three generally useful techniques for extracting regular parallelism from irregular computations: dynamic thread mapping with a work list, kernel stage decoupling, and kernel slicing. We discuss the performance impact of these techniques and suggest further opportunities for improvement.