Search for: All records

Convolutional neural networks (CNNs), a class of deep learning models, have experienced recent success in modeling sensory cortices and retinal circuits through optimizing performance on machine learning tasks, otherwise known as task optimization. Previous research has shown task-optimized CNNs to be capable of providing explanations as to why the retina efficiently encodes natural stimuli and how certain retinal cell types are involved in efficient encoding. In our work, we sought to use task-optimized CNNs as a means of explaining computational mechanisms responsible for motion-selective retinal circuits. We designed a biologically constrained CNN and optimized its performance on a motion-classification task. We drew inspiration from psychophysics, deep learning, and systems neuroscience literature to develop a toolbox of methods to reverse engineer the computational mechanisms learned in our model. Through reverse engineering our model, we proposed a computational mechanism in which direction-selective ganglion cells and starburst amacrine cells, both experimentally observed retinal cell types, emerge in our model to discriminate among moving stimuli. This emergence suggests that direction-selective circuits in the retina are ecologically designed to robustly discriminate among moving stimuli. Our results and methods also provide a framework for how to build more interpretable deep learning models and how to understand them. 

Convolutional neural networks (CNN) are an emerging technique in modeling neural circuits and have been shown to converge to biologically plausible functionality in cortical circuits via task-optimization. This functionality has not been observed in CNN models of retinal circuits via task-optimization. We sought to observe this convergence in retinal circuits by designing a biologically inspired CNN model of a motion-detection retinal circuit and optimizing it to solve a motion-classification task. The learned weights and parameters indicated that the CNN converged to direction-sensitive ganglion and amacrine cells, cell types that have been observed in biology, and provided evidence that task-optimization is a fair method of building retinal models. The analysis used to understand the functionality of our CNN also indicates that biologically constrained deep learning models are easier to reason about their underlying mechanisms than traditional deep learning models. 

Convolutional neural networks (CNN) are an emerging technique in modeling neural circuits and have been shown to converge to biologically plausible functionality in cortical circuits via task-optimization. This functionality has not been observed in CNN models of retinal circuits via task-optimization. We sought to observe this convergence in retinal circuits by designing a biologically inspired CNN model of a motion-detection retinal circuit and optimizing it to solve a motion-classification task. The learned weights and parameters indicated that the CNN converged to direction-sensitive ganglion and amacrine cells, cell types that have been observed in biology, and provided evidence that task-optimization is a fair method of building retinal models. The analysis used to understand the functionality of our CNN also indicates that biologically constrained deep learning models are easier to reason about their underlying mechanisms than traditional deep learning models. 

Abstract Generative Adversarial Networks trained on samples of simulated or actual events have been proposed as a way of generating large simulated datasets at a reduced computational cost. In this work, a novel approach to perform the simulation of photodetector signals from the time projection chamber of the EXO-200 experiment is demonstrated. The method is based on a Wasserstein Generative Adversarial Network — a deep learning technique allowing for implicit non-parametric estimation of the population distribution for a given set of objects. Our network is trained on real calibration data using raw scintillation waveforms as input. We find that it is able to produce high-quality simulated waveforms an order of magnitude faster than the traditional simulation approach and, importantly, generalize from the training sample and discern salient high-level features of the data. In particular, the network correctly deduces position dependency of scintillation light response in the detector and correctly recognizes dead photodetector channels. The network output is then integrated into the EXO-200 analysis framework to show that the standard EXO-200 reconstruction routine processes the simulated waveforms to produce energy distributions comparable to that of real waveforms. Finally, the remaining discrepancies and potential ways to improve the approach further are highlighted. 

Abstract We study a possible calibration technique for the nEXO experiment using a 127 Xe electron capture source. nEXO is a next-generation search for neutrinoless double beta decay (0 νββ ) that will use a 5-tonne, monolithic liquid xenon time projection chamber (TPC). The xenon, used both as source and detection medium, will be enriched to 90% in 136 Xe. To optimize the event reconstruction and energy resolution, calibrations are needed to map the position- and time-dependent detector response. The 36.3 day half-life of 127 Xe and its small Q-value compared to that of 136 Xe 0 νββ would allow a small activity to be maintained continuously in the detector during normal operations without introducing additional backgrounds, thereby enabling in-situ calibration and monitoring of the detector response. In this work we describe a process for producing the source and preliminary experimental tests. We then use simulations to project the precision with which such a source could calibrate spatial corrections to the light and charge response of the nEXO TPC.