Learn More
As machine learning methods gain popularity across different fields, acquiring labeled training datasets has become the primary bottleneck in the machine learning pipeline. Recently generative models have been used to create and label large amounts of training data, albeit noisily. The output of these generative models is then used to train a discriminative(More)
Modern machine learning techniques, such as deep learning, often use discriminative models that require large amounts of labeled data. An alternative approach is to use a generative model, which leverages heuristics from domain experts to train on unlabeled data. Domain experts often prefer to use generative models because they " tell a story " about their(More)
We propose a new algorithm for recovering both complex field (phase and amplitude) and source distribution (illumination spatial coherence) from a stack of intensity images captured through focus. The joint recovery is formulated as a nonlinear least-square-error optimization problem, which is solved iteratively by a modified Gauss-Newton method. We derive(More)
In microscopy, shot noise dominates image formation , which can be modeled as a Poisson process. The Richardson-Lucy method tends to converge slowly for large problems and is not flexible to the addition of non-differentiable priors. In this project, proximal algorithms like ADMM and Chambolle-Pock are applied to three dimensional deconvolution and are(More)
Inverted bulk heterojunction solar cells based on low temperature solution processed squaraine (SQ) and [6,6]-phenyl C71 butyric acid methyl-ester (PC71BM) with varying blend ratios were made in air. An optimized bulk heterojunction device of SQ and PC71BM (with a blend ratio of 1 : 6) showed a power conversion efficiency (PCE) of 2.45% with an incident(More)
  • 1