Figure 1: Overview of the classifier trained for task prediction. (a) Combine and shuffle the input files for training in the next stage of exploratory analysis. (b) Feature selection to be done in this stage. (c) Feed the task-specific user file with selected features into the trained classifier. (d) Classifier predictions are analyzed in the form of a confusion matrix shown in (e).
ABSTRACTYarbus' claim to decode the observer's task from eye movements has received mixed reactions. In this paper, we have supported the hypothesis that it is possible to decode the task. We conducted an exploratory analysis on the dataset by projecting features and data points into a scatter plot to visualize the nuance properties for each task. Following this analysis, we eliminated highly correlated features before training an SVM and Ada Boosting classifier to predict the tasks from this filtered eye movements data. We achieve an accuracy of 95.4% on this task classification problem and hence, support the hypothesis that task classification is possible from a user's eye movement data.
Figure 1: A B C: Interface of our Interactive Configuration Explorer (ICE) tool used to explore high dimensional parameter spaces. This example shows the use of the ICE in a computer systems performance optimization scenario. A is the Parameter Explorer. It shows the distribution and statistics of the numerical target variable in the context of the various categorical variables (or parameters), labeled by the green buttons at the bottom of the interface (e.g., Workload, File System). Each parameter has levels e.g., Workload has 4 levels (dbsrvr, filesrvr, mailsrvr, and websrvr), and each level has an associated bar displaying the statistical information about the numerical target variable (here, system throughput) for this level. Analysts can interactively deselect (and select) parameter levels to filter out the associated parameter configurations throughout. B is the Aggregate View, which visualizes the joint distributions of all currently selected parameter levels. C is the Provenance Terminal, to keep track of the changes in the target variable over the course of the user interactions. D shows the information contained in each bar inside the Parameter Explorer and Aggregate View.
Fig. 1. Our visual steering interface purposed to guide analysts in the task of constructing the best performing deep neural network architecture for a given application using a one-shot search algorithm. The first section is the Lego View where the analyst can create and edit different components of a large neural network with simple drag and drop operations. The Lego View visualizes the different neural network components along with their parameters. An initial large neural network is treated as a super graph (shown in the Graph View) and the problem of finding the best performing neural network architecture is framed as searching for the respective subgraph in this super graph. The Graph View visualizes the super graph where each node is a block (sequence of neural network components). The One-Shot Search algorithm evaluates the subgraphs of this super graph iteratively, gauges their accuracy with regards to a test dataset and provides a fitness score for each node in the graph (Block Information view). The subgraphs are then projected as points into the scatterplot in the Search Space view and colored based on their evaluation accuracy. Analysts can filter and analyze a specific region in the subgraph search space with zoom and pan operations in the Search Space View. Finally, all blocks with high fitness scores are combined to create the best performing candidate neural network architecture.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.