Dataset Information

XDream: Finding preferred stimuli for visual neurons using generative networks and gradient-free optimization.

ABSTRACT: A longstanding question in sensory neuroscience is what types of stimuli drive neurons to fire. The characterization of effective stimuli has traditionally been based on a combination of intuition, insights from previous studies, and luck. A new method termed XDream (EXtending DeepDream with real-time evolution for activation maximization) combined a generative neural network and a genetic algorithm in a closed loop to create strong stimuli for neurons in the macaque visual cortex. Here we extensively and systematically evaluate the performance of XDream. We use ConvNet units as in silico models of neurons, enabling experiments that would be prohibitive with biological neurons. We evaluated how the method compares to brute-force search, and how well the method generalizes to different neurons and processing stages. We also explored design and parameter choices. XDream can efficiently find preferred features for visual units without any prior knowledge about them. XDream extrapolates to different layers, architectures, and developmental regimes, performing better than brute-force search, and often better than exhaustive sampling of >1 million images. Furthermore, XDream is robust to choices of multiple image generators, optimization algorithms, and hyperparameters, suggesting that its performance is locally near-optimal. Lastly, we found no significant advantage to problem-specific parameter tuning. These results establish expectations and provide practical recommendations for using XDream to investigate neural coding in biological preparations. Overall, XDream is an efficient, general, and robust algorithm for uncovering neuronal tuning preferences using a vast and diverse stimulus space. XDream is implemented in Python, released under the MIT License, and works on Linux, Windows, and MacOS.

SUBMITTER: Xiao W

PROVIDER: S-EPMC7316361 | biostudies-literature | 2020 Jun

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

XDream: Finding preferred stimuli for visual neurons using generative networks and gradient-free optimization.

Xiao Will W Kreiman Gabriel G

PLoS computational biology 20200615 6

A longstanding question in sensory neuroscience is what types of stimuli drive neurons to fire. The characterization of effective stimuli has traditionally been based on a combination of intuition, insights from previous studies, and luck. A new method termed XDream (EXtending DeepDream with real-time evolution for activation maximization) combined a generative neural network and a genetic algorithm in a closed loop to create strong stimuli for neurons in the macaque visual cortex. Here we exten ...[more]

PMID: 32542056

Similar Datasets

Project description:BackgroundThere are no explicit guidelines or tools available to support clinicians in selecting exercise therapy modalities according to the characteristics of individual patients despite the apparent need.ObjectiveThis study develops a methodology based on a novel multiobjective optimization model and examines its feasibility as a decision support tool to support healthcare professionals in comparing different modalities and identifying the most preferred one based on a patient's needs.MethodsThirty-one exercise therapy modalities were considered from 21 randomized controlled trials. A novel interactive multiobjective optimization model was designed to characterize the efficacy of an exercise therapy modality based on five objectives: minimizing cost, maximizing pain reduction, maximizing disability improvement, minimizing the number of supervised sessions, and minimizing the length of the treatment period. An interactive model incorporates clinicians' preferences in finding the most preferred exercise therapy modality for each need. Multiobjective optimization methods are mathematical algorithms designed to identify the optimal balance between multiple conflicting objectives among available solutions/alternatives. They explicitly evaluate the conflicting objectives and support decision-makers in identifying the best balance. An experienced research-oriented physiotherapist was involved as a decision-maker in the interactive solution process testing the proposed decision support tool.ResultsThe proposed methodology design and interactive process of the tool, including preference information, graphs, and exercise suggestions following the preferences, can help clinicians to find the most preferred exercise therapy modality based on a patient's needs and health status; paving the way to individualize recommendations.ConclusionsWe examined the feasibility of our decision support tool using an interactive multiobjective optimization method designed to help clinicians balance between conflicting objectives to find the most preferred exercise therapy modality for patients with knee osteoarthritis. The proposed methodology is generic enough to be applied in any field of medical and healthcare settings, where several alternative treatment options exist.KEY MESSAGESWe demonstrate the potential of applying Interactive multiobjective optimization methods in a decision support tool to help clinicians compare different exercise therapy modalities and identify the most preferred one based on a patient's needs.The usability of the proposed decision support tool is tested and demonstrated in prescribing exercise therapy modalities to treat knee osteoarthritis patients.

Project description:Chemometric modeling for spectral data is considered a key technology in biopharmaceutical processing to realize real-time process control and release testing. Machine learning (ML) models have been shown to increase the accuracy of various spectral regression and classification tasks, remove challenging preprocessing steps for spectral data, and promise to improve the transferability of models when compared to commonly applied, linear methods. The training and optimization of ML models require large data sets which are not available in the context of biopharmaceutical processing. Generative methods to extend data sets with realistic in silico samples, so-called data augmentation, may provide the means to alleviate this challenge. In this study, we develop and implement a novel data augmentation method for generating in silico spectral data based on local estimation of pure component profiles for training convolutional neural network (CNN) models using four data sets. We simultaneously tune hyperparameters associated with data augmentation and the neural network architecture using Bayesian optimization. Finally, we compare the optimized CNN models with partial least-squares regression models (PLS) in terms of accuracy, robustness, and interpretability. The proposed data augmentation method is shown to produce highly realistic spectral data by adapting the estimates of the pure component profiles to the sampled concentration regimes. Augmenting CNNs with the in silico spectral data is shown to improve the prediction accuracy for the quantification of monoclonal antibody (mAb) size variants by up to 50% in comparison to single-response PLS models. Bayesian structure optimization suggests that multiple convolutional blocks are beneficial for model accuracy and enable transfer across different data sets. Model-agnostic feature importance methods and synthetic noise perturbation are used to directly compare the optimized CNNs with PLS models. This enables the identification of wavelength regions critical for model performance and suggests increased robustness against Gaussian white noise and wavelength shifts of the CNNs compared to the PLS models.

Dataset Information

XDream: Finding preferred stimuli for visual neurons using generative networks and gradient-free optimization.

Publications

XDream: Finding preferred stimuli for visual neurons using generative networks and gradient-free optimization.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets